Spaces:
Running
Running
Yotam-Perlitz
commited on
Commit
•
871f49c
1
Parent(s):
697d2f9
re-write cache
Browse filesSigned-off-by: Yotam-Perlitz <y.perlitz@ibm.com>
- cache/aggregate_scoress_cache_05c0405c5253dda90dc632e052accfd2.csv +0 -130
- cache/agreements_cache_05c0405c5253dda90dc632e052accfd2.csv +0 -763
- cache/agreements_cache_5e66a88dab42480065db47711c55c458.csv +132 -132
- cache/allbenchs_cache_05c0405c5253dda90dc632e052accfd2.csv +0 -0
- cache/allbenchs_cache_5e66a88dab42480065db47711c55c458.csv +0 -0
cache/aggregate_scoress_cache_05c0405c5253dda90dc632e052accfd2.csv
DELETED
|
@@ -1,130 +0,0 @@
|
|
| 1 |
-
model,score
|
| 2 |
-
gemini_1_5_pro_api_0409_preview,1.0
|
| 3 |
-
gemini_1_5_pro_exp_0801,0.9921875
|
| 4 |
-
chatgpt_4o_latest,0.984375
|
| 5 |
-
gpt_3_5_turbo_0314,0.9765625
|
| 6 |
-
bard_jan_24_gemini_pro,0.96875
|
| 7 |
-
claude_1,0.9609375
|
| 8 |
-
gemini_advanced_0514,0.953125
|
| 9 |
-
llama3_1_70b_instruct,0.9453125
|
| 10 |
-
gpt_4o_2024_05_13,0.9375
|
| 11 |
-
gpt_4o_2024_08_06,0.9296875
|
| 12 |
-
gpt_4o_mini_2024_07_18,0.921875
|
| 13 |
-
claude_3_5_sonnet_20240620,0.9140625
|
| 14 |
-
claude_3_opus_20240229,0.90625
|
| 15 |
-
athene_70b_0725,0.8984375
|
| 16 |
-
gemini_pro_dev_api,0.890625
|
| 17 |
-
claude_2_0,0.8828125
|
| 18 |
-
glm_4_0520,0.875
|
| 19 |
-
nemotron_4_340b_instruct,0.8671875
|
| 20 |
-
yi_large_preview,0.859375
|
| 21 |
-
llama_2_70b_chat,0.8515625
|
| 22 |
-
reka_core_20240722,0.84375
|
| 23 |
-
gemini_1_5_pro_api_0514,0.8359375
|
| 24 |
-
gemini_pro,0.828125
|
| 25 |
-
llama3_1_405b_instruct,0.8203125
|
| 26 |
-
mistral_large_2407,0.8125
|
| 27 |
-
gpt_4_turbo_2024_04_09,0.8046875
|
| 28 |
-
gpt_4_1106_preview,0.796875
|
| 29 |
-
gpt_3_5_turbo_0613,0.7890625
|
| 30 |
-
gpt_4_0125_preview,0.78125
|
| 31 |
-
glm_4_0116,0.7734375
|
| 32 |
-
zephyr_orpo_141b_a35b_v0_1,0.765625
|
| 33 |
-
qwen_max_0428,0.7578125
|
| 34 |
-
claude_instant_1,0.75
|
| 35 |
-
yi_large,0.7421875
|
| 36 |
-
deepseek_coder_v2_0724,0.734375
|
| 37 |
-
deepseek_v2_api_0628,0.7265625
|
| 38 |
-
gemini_1_5_flash_api_0514,0.71875
|
| 39 |
-
llama3_70b_instruct,0.7109375
|
| 40 |
-
command_r_plus,0.703125
|
| 41 |
-
gpt_4_0314,0.6953125
|
| 42 |
-
claude_2_1,0.6875
|
| 43 |
-
wizardlm_70b,0.6796875
|
| 44 |
-
gemma_2_27b_it,0.671875
|
| 45 |
-
dolphin_2_2_1_mistral_7b,0.6640625
|
| 46 |
-
guanaco_33b,0.65625
|
| 47 |
-
nous_hermes_2_mixtral_8x7b_dpo,0.6484375
|
| 48 |
-
wizardlm_13b,0.640625
|
| 49 |
-
mpt_30b_chat,0.6328125
|
| 50 |
-
qwen1_5_110b_chat,0.625
|
| 51 |
-
claude_3_sonnet_20240229,0.6171875
|
| 52 |
-
mistral_next,0.609375
|
| 53 |
-
deepseek_coder_v2,0.6015625
|
| 54 |
-
reka_flash_21b_20240226_online,0.59375
|
| 55 |
-
starling_lm_7b_beta,0.5859375
|
| 56 |
-
llama2_70b_steerlm_chat,0.578125
|
| 57 |
-
mistral_medium,0.5703125
|
| 58 |
-
llama_2_13b_chat,0.5625
|
| 59 |
-
tulu_2_dpo_70b,0.5546875
|
| 60 |
-
reka_core_20240501,0.546875
|
| 61 |
-
gpt_4_0613,0.5390625
|
| 62 |
-
deepseek_llm_67b_chat,0.53125
|
| 63 |
-
solar_10_7b_instruct_v1_0,0.5234375
|
| 64 |
-
openchat_3_5_0106,0.515625
|
| 65 |
-
reka_flash_20240722,0.5078125
|
| 66 |
-
gemma_2_9b_it,0.5
|
| 67 |
-
llama3_1_8b_instruct,0.4921875
|
| 68 |
-
openchat_3_5,0.484375
|
| 69 |
-
pplx_7b_online,0.4765625
|
| 70 |
-
qwen1_5_72b_chat,0.46875
|
| 71 |
-
zephyr_7b_alpha,0.4609375
|
| 72 |
-
claude_3_haiku_20240307,0.453125
|
| 73 |
-
starling_lm_7b_alpha,0.4453125
|
| 74 |
-
reka_flash_21b_20240226,0.4375
|
| 75 |
-
mistral_large_2402,0.4296875
|
| 76 |
-
gpt_3_5_turbo_1106,0.421875
|
| 77 |
-
qwen1_5_7b_chat,0.4140625
|
| 78 |
-
reka_flash_preview_20240611,0.40625
|
| 79 |
-
yi_1_5_34b_chat,0.3984375
|
| 80 |
-
openhermes_2_5_mistral_7b,0.390625
|
| 81 |
-
codellama34b_instruct,0.3828125
|
| 82 |
-
qwen1_5_14b_chat,0.375
|
| 83 |
-
yi_34b_chat,0.3671875
|
| 84 |
-
pplx_70b_online,0.359375
|
| 85 |
-
qwen2_72b_instruct,0.3515625
|
| 86 |
-
dbrx_instructruct_preview,0.34375
|
| 87 |
-
llama3_8b_instruct,0.3359375
|
| 88 |
-
falcon_180b_chat,0.328125
|
| 89 |
-
palm_2,0.3203125
|
| 90 |
-
qwen_14b_chat,0.3125
|
| 91 |
-
stripedhyena_nous_7b,0.3046875
|
| 92 |
-
qwen1_5_32b_chat,0.296875
|
| 93 |
-
command_r,0.2890625
|
| 94 |
-
gemma_7b_it,0.28125
|
| 95 |
-
zephyr_7b_beta,0.2734375
|
| 96 |
-
mixtral_8x22b_instruct_v0_1,0.265625
|
| 97 |
-
vicuna_7b,0.2578125
|
| 98 |
-
snowflake_arctic_instruct,0.25
|
| 99 |
-
vicuna_33b,0.2421875
|
| 100 |
-
gemma_2_2b_it,0.234375
|
| 101 |
-
koala_13b,0.2265625
|
| 102 |
-
gpt_3_5_turbo_0125,0.21875
|
| 103 |
-
mistral_7b_instruct,0.2109375
|
| 104 |
-
llama_2_7b_chat,0.203125
|
| 105 |
-
mistral_7b_instruct_v0_2,0.1953125
|
| 106 |
-
gemma_1_1_7b_it,0.1875
|
| 107 |
-
gpt4all_13b_snoozy,0.1796875
|
| 108 |
-
phi_3_small_8k_instruct,0.171875
|
| 109 |
-
olmo_7b_instruct,0.1640625
|
| 110 |
-
phi_3_mini_4k_instruct,0.15625
|
| 111 |
-
phi_3_mini_128k_instruct,0.1484375
|
| 112 |
-
rwkv_4_raven_14b,0.140625
|
| 113 |
-
vicuna_13b,0.1328125
|
| 114 |
-
codellama_70b_instruct,0.125
|
| 115 |
-
mpt_7b_chat,0.1171875
|
| 116 |
-
mixtral_8x7b_instruct_v0_1,0.109375
|
| 117 |
-
phi_3_medium_4k_instruct,0.1015625
|
| 118 |
-
gemma_2b_it,0.09375
|
| 119 |
-
phi_3_mini_4k_instruct_june_2024,0.0859375
|
| 120 |
-
qwen1_5_4b_chat,0.078125
|
| 121 |
-
chatglm_6b,0.0703125
|
| 122 |
-
alpaca_13b,0.0625
|
| 123 |
-
gemma_1_1_2b_it,0.0546875
|
| 124 |
-
chatglm2_6b,0.046875
|
| 125 |
-
stablelm_tuned_alpha_7b,0.0390625
|
| 126 |
-
chatglm3_6b,0.03125
|
| 127 |
-
oasst_pythia_12b,0.0234375
|
| 128 |
-
llama_13b,0.015625
|
| 129 |
-
fastchat_t5_3b,0.0078125
|
| 130 |
-
dolly_v2_12b,0.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cache/agreements_cache_05c0405c5253dda90dc632e052accfd2.csv
DELETED
|
@@ -1,763 +0,0 @@
|
|
| 1 |
-
scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
|
| 2 |
-
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5455447255899809,0.0614649096074132
|
| 3 |
-
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111
|
| 4 |
-
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5455447255899809,0.0614649096074132
|
| 5 |
-
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.2857142857142857,0.39875992063492066
|
| 6 |
-
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 7 |
-
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.47280542884465016,0.10506382347888965
|
| 8 |
-
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 9 |
-
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 10 |
-
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 11 |
-
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 12 |
-
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 13 |
-
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 14 |
-
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.2857142857142857,0.39875992063492066
|
| 15 |
-
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 16 |
-
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5455447255899809,0.0614649096074132
|
| 17 |
-
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 18 |
-
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 19 |
-
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 20 |
-
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 21 |
-
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762
|
| 22 |
-
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.47280542884465016,0.10506382347888965
|
| 23 |
-
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.07142857142857142,0.9048611111111111
|
| 24 |
-
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 25 |
-
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 26 |
-
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 27 |
-
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 28 |
-
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 29 |
-
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.2857142857142857,0.39875992063492066
|
| 30 |
-
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 31 |
-
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 32 |
-
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.2545875386086578,0.38281014365989596
|
| 33 |
-
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 34 |
-
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5455447255899809,0.0614649096074132
|
| 35 |
-
LMSys Arena,chatbot_arena_241104.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
|
| 36 |
-
LMSys Arena,chatbot_arena_241104.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
|
| 37 |
-
LMSys Arena,chatbot_arena_241104.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05
|
| 38 |
-
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 39 |
-
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 40 |
-
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762
|
| 41 |
-
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.21428571428571427,0.5484126984126985
|
| 42 |
-
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 43 |
-
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 44 |
-
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 45 |
-
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 46 |
-
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 47 |
-
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 48 |
-
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 49 |
-
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
|
| 50 |
-
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 51 |
-
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 52 |
-
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 53 |
-
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 54 |
-
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 55 |
-
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 56 |
-
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 57 |
-
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 58 |
-
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 59 |
-
tablebench_overall_dp,tablebench_241002.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111
|
| 60 |
-
tablebench_overall_dp,tablebench_241002.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 61 |
-
tablebench_overall_dp,tablebench_241002.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 62 |
-
trustworthy_average,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 63 |
-
trustworthy_average,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 64 |
-
trustworthy_average,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 65 |
-
trustworthy_non_toxicity,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,0,0.14285714285714285,0.7195436507936508
|
| 66 |
-
trustworthy_non_toxicity,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,1,0.14285714285714285,0.7195436507936508
|
| 67 |
-
trustworthy_non_toxicity,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,2,0.14285714285714285,0.7195436507936508
|
| 68 |
-
trustworthy_non_stereotype,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 69 |
-
trustworthy_non_stereotype,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 70 |
-
trustworthy_non_stereotype,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 71 |
-
trustworthy_advglue_pp,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 72 |
-
trustworthy_advglue_pp,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 73 |
-
trustworthy_advglue_pp,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 74 |
-
trustworthy_ood,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 75 |
-
trustworthy_ood,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 76 |
-
trustworthy_ood,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 77 |
-
trustworthy_adv_demo,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 78 |
-
trustworthy_adv_demo,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 79 |
-
trustworthy_adv_demo,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 80 |
-
trustworthy_privacy,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,0,0.07142857142857142,0.9048611111111111
|
| 81 |
-
trustworthy_privacy,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,1,0.07142857142857142,0.9048611111111111
|
| 82 |
-
trustworthy_privacy,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 83 |
-
trustworthy_ethics,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 84 |
-
trustworthy_ethics,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 85 |
-
trustworthy_ethics,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 86 |
-
trustworthy_fairness,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,0,-0.6910233190806424,0.017844011512848347
|
| 87 |
-
trustworthy_fairness,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,1,-0.6910233190806424,0.017844011512848347
|
| 88 |
-
trustworthy_fairness,llm_trustworthy_241001.csv,aggregate,aggregate,kendall,random,8,2,-0.6910233190806424,0.017844011512848347
|
| 89 |
-
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 90 |
-
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 91 |
-
OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 92 |
-
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 93 |
-
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 94 |
-
OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 95 |
-
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 96 |
-
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 97 |
-
OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 98 |
-
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 99 |
-
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 100 |
-
OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 101 |
-
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 102 |
-
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 103 |
-
OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 104 |
-
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.036369648372665396,0.9007802600472398
|
| 105 |
-
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.07142857142857142,0.9048611111111111
|
| 106 |
-
OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,-0.036369648372665396,0.9007802600472398
|
| 107 |
-
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4447495899966607,0.1315867602811863
|
| 108 |
-
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2545875386086578,0.38281014365989596
|
| 109 |
-
OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.40006613209931935,0.17023995462900499
|
| 110 |
-
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.2857142857142857,0.39875992063492066
|
| 111 |
-
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 112 |
-
OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.21428571428571427,0.5484126984126985
|
| 113 |
-
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 114 |
-
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 115 |
-
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 116 |
-
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 117 |
-
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 118 |
-
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 119 |
-
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 120 |
-
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 121 |
-
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762
|
| 122 |
-
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
|
| 123 |
-
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 124 |
-
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
|
| 125 |
-
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 126 |
-
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.14285714285714285,0.7195436507936508
|
| 127 |
-
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 128 |
-
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111
|
| 129 |
-
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762
|
| 130 |
-
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
|
| 131 |
-
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 132 |
-
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 133 |
-
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762
|
| 134 |
-
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111
|
| 135 |
-
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 136 |
-
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6910233190806425,0.017844011512848347
|
| 137 |
-
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 138 |
-
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.47280542884465016,0.10506382347888965
|
| 139 |
-
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6182840223353117,0.0340492747686748
|
| 140 |
-
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 141 |
-
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 142 |
-
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 143 |
-
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 144 |
-
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 145 |
-
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
|
| 146 |
-
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 147 |
-
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 148 |
-
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 149 |
-
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,0,0.21428571428571427,0.5484126984126985
|
| 150 |
-
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762
|
| 151 |
-
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,2,0.2545875386086578,0.38281014365989596
|
| 152 |
-
HELM AirBench Security Risks,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.42857142857142855,0.17886904761904762
|
| 153 |
-
HELM AirBench Security Risks,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.2857142857142857,0.39875992063492066
|
| 154 |
-
HELM AirBench Security Risks,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.21428571428571427,0.5484126984126985
|
| 155 |
-
HELM AirBench Operational Misuses,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 156 |
-
HELM AirBench Operational Misuses,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.18184824186332696,0.5330356744917513
|
| 157 |
-
HELM AirBench Operational Misuses,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.42857142857142855,0.17886904761904762
|
| 158 |
-
HELM AirBench Violence & Extremism,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 159 |
-
HELM AirBench Violence & Extremism,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.7142857142857142,0.014136904761904762
|
| 160 |
-
HELM AirBench Violence & Extremism,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.3571428571428571,0.27509920634920637
|
| 161 |
-
HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 162 |
-
HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.7142857142857142,0.014136904761904762
|
| 163 |
-
HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.2857142857142857,0.39875992063492066
|
| 164 |
-
HELM AirBench Sexual Content,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.42857142857142855,0.17886904761904762
|
| 165 |
-
HELM AirBench Sexual Content,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 166 |
-
HELM AirBench Sexual Content,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.42857142857142855,0.17886904761904762
|
| 167 |
-
HELM AirBench Child Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 168 |
-
HELM AirBench Child Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 169 |
-
HELM AirBench Child Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.42857142857142855,0.17886904761904762
|
| 170 |
-
HELM AirBench Self Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.40006613209931935,0.17023995462900499
|
| 171 |
-
HELM AirBench Self Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 172 |
-
HELM AirBench Self Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.40006613209931935,0.17023995462900499
|
| 173 |
-
HELM AirBench Political Usage,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 174 |
-
HELM AirBench Political Usage,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 175 |
-
HELM AirBench Political Usage,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.3571428571428571,0.27509920634920637
|
| 176 |
-
HELM AirBench Economic Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 177 |
-
HELM AirBench Economic Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.6182840223353117,0.0340492747686748
|
| 178 |
-
HELM AirBench Economic Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.3571428571428571,0.27509920634920637
|
| 179 |
-
HELM AirBench Deception,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.4999999999999999,0.10868055555555556
|
| 180 |
-
HELM AirBench Deception,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.6428571428571428,0.03115079365079365
|
| 181 |
-
HELM AirBench Deception,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.40006613209931935,0.17023995462900499
|
| 182 |
-
HELM AirBench Manipulation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 183 |
-
HELM AirBench Manipulation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.6182840223353117,0.0340492747686748
|
| 184 |
-
HELM AirBench Manipulation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.3571428571428571,0.27509920634920637
|
| 185 |
-
HELM AirBench Defamation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.40006613209931935,0.17023995462900499
|
| 186 |
-
HELM AirBench Defamation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.4999999999999999,0.10868055555555556
|
| 187 |
-
HELM AirBench Defamation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.40006613209931935,0.17023995462900499
|
| 188 |
-
HELM AirBench Fundamental Rights,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.6182840223353117,0.0340492747686748
|
| 189 |
-
HELM AirBench Fundamental Rights,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 190 |
-
HELM AirBench Fundamental Rights,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.41576092031014994,0.1612822677790775
|
| 191 |
-
HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 192 |
-
HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 193 |
-
HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.4999999999999999,0.10868055555555556
|
| 194 |
-
HELM AirBench Privacy,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 195 |
-
HELM AirBench Privacy,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.3571428571428571,0.27509920634920637
|
| 196 |
-
HELM AirBench Privacy,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.21428571428571427,0.5484126984126985
|
| 197 |
-
HELM AirBench Criminal Activities,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 198 |
-
HELM AirBench Criminal Activities,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 199 |
-
HELM AirBench Criminal Activities,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.42857142857142855,0.17886904761904762
|
| 200 |
-
HELM AirBench AIR Score,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,-0.6428571428571428,0.03115079365079365
|
| 201 |
-
HELM AirBench AIR Score,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 202 |
-
HELM AirBench AIR Score,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,-0.47280542884465016,0.10506382347888965
|
| 203 |
-
OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 204 |
-
OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 205 |
-
OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 206 |
-
OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.21428571428571427,0.5484126984126985
|
| 207 |
-
OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 208 |
-
OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 209 |
-
OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 210 |
-
OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 211 |
-
OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,-0.21428571428571427,0.5484126984126985
|
| 212 |
-
OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 213 |
-
OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 214 |
-
OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 215 |
-
OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 216 |
-
OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 217 |
-
OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.14285714285714285,0.7195436507936508
|
| 218 |
-
OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 219 |
-
OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6910233190806425,0.017844011512848347
|
| 220 |
-
OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.40006613209931935,0.17023995462900499
|
| 221 |
-
OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 222 |
-
OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381
|
| 223 |
-
OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
|
| 224 |
-
OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 225 |
-
OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 226 |
-
OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,-0.14285714285714285,0.7195436507936508
|
| 227 |
-
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,0,0.32732683535398854,0.2618277009271762
|
| 228 |
-
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 229 |
-
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,2,0.21428571428571427,0.5484126984126985
|
| 230 |
-
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 231 |
-
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 232 |
-
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 233 |
-
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 234 |
-
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2545875386086578,0.38281014365989596
|
| 235 |
-
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 236 |
-
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 237 |
-
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 238 |
-
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 239 |
-
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 240 |
-
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 241 |
-
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 242 |
-
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 243 |
-
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 244 |
-
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,-0.07142857142857142,0.9048611111111111
|
| 245 |
-
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 246 |
-
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 247 |
-
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 248 |
-
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 249 |
-
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 250 |
-
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 251 |
-
Enkrypt AI Safety,enkrypt_ai_safety_240916.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 252 |
-
Enkrypt AI Safety,enkrypt_ai_safety_240916.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 253 |
-
Enkrypt AI Safety,enkrypt_ai_safety_240916.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 254 |
-
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 255 |
-
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 256 |
-
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 257 |
-
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 258 |
-
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 259 |
-
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
|
| 260 |
-
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 261 |
-
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 262 |
-
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
|
| 263 |
-
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 264 |
-
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 265 |
-
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 266 |
-
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 267 |
-
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 268 |
-
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 269 |
-
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 270 |
-
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 271 |
-
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 272 |
-
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 273 |
-
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 274 |
-
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 275 |
-
Decentralized Arena (0-1 Normalized),dec_arena_241022.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 276 |
-
Decentralized Arena (0-1 Normalized),dec_arena_241022.csv,aggregate,aggregate,kendall,random,8,1,0.40006613209931935,0.17023995462900499
|
| 277 |
-
Decentralized Arena (0-1 Normalized),dec_arena_241022.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 278 |
-
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 279 |
-
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 280 |
-
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,2,0.21428571428571427,0.5484126984126985
|
| 281 |
-
AgentBench,agenbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.32732683535398854,0.2618277009271762
|
| 282 |
-
AgentBench,agenbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.32732683535398854,0.2618277009271762
|
| 283 |
-
AgentBench,agenbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.32732683535398854,0.2618277009271762
|
| 284 |
-
MT-Bench,mtbench_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 285 |
-
MT-Bench,mtbench_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.6182840223353117,0.0340492747686748
|
| 286 |
-
MT-Bench,mtbench_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 287 |
-
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 288 |
-
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 289 |
-
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 290 |
-
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 291 |
-
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 292 |
-
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 293 |
-
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 294 |
-
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.0,1.0
|
| 295 |
-
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.14285714285714285,0.7195436507936508
|
| 296 |
-
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 297 |
-
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 298 |
-
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.21428571428571427,0.5484126984126985
|
| 299 |
-
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 300 |
-
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 301 |
-
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 302 |
-
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 303 |
-
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 304 |
-
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.0,1.0
|
| 305 |
-
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 306 |
-
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 307 |
-
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 308 |
-
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 309 |
-
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 310 |
-
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 311 |
-
eq_bench,eqbench_240912.csv,aggregate,aggregate,kendall,random,8,0,0.14285714285714285,0.7195436507936508
|
| 312 |
-
eq_bench,eqbench_240912.csv,aggregate,aggregate,kendall,random,8,1,0.07142857142857142,0.9048611111111111
|
| 313 |
-
eq_bench,eqbench_240912.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 314 |
-
magi_hard,eqbench_240912.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 315 |
-
magi_hard,eqbench_240912.csv,aggregate,aggregate,kendall,random,8,1,-0.07142857142857142,0.9048611111111111
|
| 316 |
-
magi_hard,eqbench_240912.csv,aggregate,aggregate,kendall,random,8,2,-0.07142857142857142,0.9048611111111111
|
| 317 |
-
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 318 |
-
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,-0.07142857142857142,0.9048611111111111
|
| 319 |
-
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 320 |
-
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 321 |
-
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.07142857142857142,0.9048611111111111
|
| 322 |
-
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 323 |
-
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.47280542884465016,0.10506382347888965
|
| 324 |
-
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.41576092031014994,0.1612822677790775
|
| 325 |
-
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762
|
| 326 |
-
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 327 |
-
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 328 |
-
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 329 |
-
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 330 |
-
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,-0.21428571428571427,0.5484126984126985
|
| 331 |
-
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 332 |
-
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6425396041156862,0.030400749685896046
|
| 333 |
-
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,-0.036369648372665396,0.9007802600472398
|
| 334 |
-
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 335 |
-
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 336 |
-
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 337 |
-
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.47280542884465016,0.10506382347888965
|
| 338 |
-
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 339 |
-
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.14285714285714285,0.7195436507936508
|
| 340 |
-
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 341 |
-
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 342 |
-
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.14285714285714285,0.7195436507936508
|
| 343 |
-
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 344 |
-
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111
|
| 345 |
-
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.47280542884465016,0.10506382347888965
|
| 346 |
-
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 347 |
-
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 348 |
-
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 349 |
-
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 350 |
-
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 351 |
-
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 352 |
-
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7637626158259734,0.008839740160738534
|
| 353 |
-
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 354 |
-
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 355 |
-
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 356 |
-
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 357 |
-
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 358 |
-
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 359 |
-
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 360 |
-
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 361 |
-
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 362 |
-
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 363 |
-
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762
|
| 364 |
-
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 365 |
-
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 366 |
-
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 367 |
-
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 368 |
-
hydrox_integrity,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 369 |
-
hydrox_integrity,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,1,0.0,1.0
|
| 370 |
-
hydrox_integrity,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,2,0.14285714285714285,0.7195436507936508
|
| 371 |
-
hydrox_overall_score,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 372 |
-
hydrox_overall_score,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,1,0.0,1.0
|
| 373 |
-
hydrox_overall_score,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,2,0.14285714285714285,0.7195436507936508
|
| 374 |
-
hydrox_privacy,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 375 |
-
hydrox_privacy,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,1,-0.07142857142857142,0.9048611111111111
|
| 376 |
-
hydrox_privacy,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,2,0.14285714285714285,0.7195436507936508
|
| 377 |
-
hydrox_safety,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 378 |
-
hydrox_safety,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,1,-0.07142857142857142,0.9048611111111111
|
| 379 |
-
hydrox_safety,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 380 |
-
hydrox_security,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 381 |
-
hydrox_security,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,1,0.0,1.0
|
| 382 |
-
hydrox_security,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 383 |
-
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,0,0.5455447255899809,0.0614649096074132
|
| 384 |
-
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111
|
| 385 |
-
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,2,0.5455447255899809,0.0614649096074132
|
| 386 |
-
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,0,0.2857142857142857,0.39875992063492066
|
| 387 |
-
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 388 |
-
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,2,0.47280542884465016,0.10506382347888965
|
| 389 |
-
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 390 |
-
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 391 |
-
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 392 |
-
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 393 |
-
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 394 |
-
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 395 |
-
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,0,0.2857142857142857,0.39875992063492066
|
| 396 |
-
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 397 |
-
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,2,0.5455447255899809,0.0614649096074132
|
| 398 |
-
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 399 |
-
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 400 |
-
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 401 |
-
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 402 |
-
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762
|
| 403 |
-
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,2,0.47280542884465016,0.10506382347888965
|
| 404 |
-
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,0,0.07142857142857142,0.9048611111111111
|
| 405 |
-
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 406 |
-
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 407 |
-
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 408 |
-
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 409 |
-
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 410 |
-
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,0,0.2857142857142857,0.39875992063492066
|
| 411 |
-
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 412 |
-
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 413 |
-
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,0,0.2545875386086578,0.38281014365989596
|
| 414 |
-
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 415 |
-
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,2,0.5455447255899809,0.0614649096074132
|
| 416 |
-
aggregate,aggregate,LMSys Arena,chatbot_arena_241104.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
|
| 417 |
-
aggregate,aggregate,LMSys Arena,chatbot_arena_241104.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
|
| 418 |
-
aggregate,aggregate,LMSys Arena,chatbot_arena_241104.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05
|
| 419 |
-
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 420 |
-
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 421 |
-
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762
|
| 422 |
-
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985
|
| 423 |
-
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 424 |
-
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 425 |
-
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 426 |
-
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 427 |
-
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 428 |
-
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 429 |
-
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 430 |
-
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
|
| 431 |
-
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 432 |
-
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 433 |
-
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 434 |
-
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 435 |
-
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 436 |
-
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 437 |
-
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 438 |
-
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 439 |
-
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 440 |
-
aggregate,aggregate,tablebench_overall_dp,tablebench_241002.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111
|
| 441 |
-
aggregate,aggregate,tablebench_overall_dp,tablebench_241002.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 442 |
-
aggregate,aggregate,tablebench_overall_dp,tablebench_241002.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 443 |
-
aggregate,aggregate,trustworthy_average,llm_trustworthy_241001.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 444 |
-
aggregate,aggregate,trustworthy_average,llm_trustworthy_241001.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 445 |
-
aggregate,aggregate,trustworthy_average,llm_trustworthy_241001.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 446 |
-
aggregate,aggregate,trustworthy_non_toxicity,llm_trustworthy_241001.csv,kendall,random,8,0,0.14285714285714285,0.7195436507936508
|
| 447 |
-
aggregate,aggregate,trustworthy_non_toxicity,llm_trustworthy_241001.csv,kendall,random,8,1,0.14285714285714285,0.7195436507936508
|
| 448 |
-
aggregate,aggregate,trustworthy_non_toxicity,llm_trustworthy_241001.csv,kendall,random,8,2,0.14285714285714285,0.7195436507936508
|
| 449 |
-
aggregate,aggregate,trustworthy_non_stereotype,llm_trustworthy_241001.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 450 |
-
aggregate,aggregate,trustworthy_non_stereotype,llm_trustworthy_241001.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 451 |
-
aggregate,aggregate,trustworthy_non_stereotype,llm_trustworthy_241001.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 452 |
-
aggregate,aggregate,trustworthy_advglue_pp,llm_trustworthy_241001.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 453 |
-
aggregate,aggregate,trustworthy_advglue_pp,llm_trustworthy_241001.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 454 |
-
aggregate,aggregate,trustworthy_advglue_pp,llm_trustworthy_241001.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 455 |
-
aggregate,aggregate,trustworthy_ood,llm_trustworthy_241001.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 456 |
-
aggregate,aggregate,trustworthy_ood,llm_trustworthy_241001.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 457 |
-
aggregate,aggregate,trustworthy_ood,llm_trustworthy_241001.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 458 |
-
aggregate,aggregate,trustworthy_adv_demo,llm_trustworthy_241001.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 459 |
-
aggregate,aggregate,trustworthy_adv_demo,llm_trustworthy_241001.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 460 |
-
aggregate,aggregate,trustworthy_adv_demo,llm_trustworthy_241001.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 461 |
-
aggregate,aggregate,trustworthy_privacy,llm_trustworthy_241001.csv,kendall,random,8,0,0.07142857142857142,0.9048611111111111
|
| 462 |
-
aggregate,aggregate,trustworthy_privacy,llm_trustworthy_241001.csv,kendall,random,8,1,0.07142857142857142,0.9048611111111111
|
| 463 |
-
aggregate,aggregate,trustworthy_privacy,llm_trustworthy_241001.csv,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 464 |
-
aggregate,aggregate,trustworthy_ethics,llm_trustworthy_241001.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 465 |
-
aggregate,aggregate,trustworthy_ethics,llm_trustworthy_241001.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 466 |
-
aggregate,aggregate,trustworthy_ethics,llm_trustworthy_241001.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 467 |
-
aggregate,aggregate,trustworthy_fairness,llm_trustworthy_241001.csv,kendall,random,8,0,-0.6910233190806424,0.017844011512848347
|
| 468 |
-
aggregate,aggregate,trustworthy_fairness,llm_trustworthy_241001.csv,kendall,random,8,1,-0.6910233190806424,0.017844011512848347
|
| 469 |
-
aggregate,aggregate,trustworthy_fairness,llm_trustworthy_241001.csv,kendall,random,8,2,-0.6910233190806424,0.017844011512848347
|
| 470 |
-
aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 471 |
-
aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 472 |
-
aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 473 |
-
aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 474 |
-
aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 475 |
-
aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 476 |
-
aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 477 |
-
aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 478 |
-
aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 479 |
-
aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 480 |
-
aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 481 |
-
aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 482 |
-
aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 483 |
-
aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 484 |
-
aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 485 |
-
aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,0,0.036369648372665396,0.9007802600472398
|
| 486 |
-
aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,1,0.07142857142857142,0.9048611111111111
|
| 487 |
-
aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,2,-0.036369648372665396,0.9007802600472398
|
| 488 |
-
aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,0,0.4447495899966607,0.1315867602811863
|
| 489 |
-
aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,1,0.2545875386086578,0.38281014365989596
|
| 490 |
-
aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,2,0.40006613209931935,0.17023995462900499
|
| 491 |
-
aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,0,0.2857142857142857,0.39875992063492066
|
| 492 |
-
aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 493 |
-
aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,2,0.21428571428571427,0.5484126984126985
|
| 494 |
-
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 495 |
-
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 496 |
-
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 497 |
-
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 498 |
-
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 499 |
-
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 500 |
-
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 501 |
-
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 502 |
-
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762
|
| 503 |
-
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
|
| 504 |
-
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 505 |
-
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
|
| 506 |
-
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 507 |
-
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,1,0.14285714285714285,0.7195436507936508
|
| 508 |
-
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 509 |
-
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111
|
| 510 |
-
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762
|
| 511 |
-
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
|
| 512 |
-
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 513 |
-
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 514 |
-
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762
|
| 515 |
-
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111
|
| 516 |
-
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 517 |
-
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,2,0.6910233190806425,0.017844011512848347
|
| 518 |
-
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 519 |
-
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,1,0.47280542884465016,0.10506382347888965
|
| 520 |
-
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,2,0.6182840223353117,0.0340492747686748
|
| 521 |
-
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 522 |
-
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 523 |
-
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 524 |
-
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 525 |
-
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 526 |
-
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
|
| 527 |
-
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 528 |
-
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 529 |
-
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 530 |
-
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985
|
| 531 |
-
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762
|
| 532 |
-
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,2,0.2545875386086578,0.38281014365989596
|
| 533 |
-
aggregate,aggregate,HELM AirBench Security Risks,helm_airbench_240916.csv,kendall,random,8,0,-0.42857142857142855,0.17886904761904762
|
| 534 |
-
aggregate,aggregate,HELM AirBench Security Risks,helm_airbench_240916.csv,kendall,random,8,1,-0.2857142857142857,0.39875992063492066
|
| 535 |
-
aggregate,aggregate,HELM AirBench Security Risks,helm_airbench_240916.csv,kendall,random,8,2,-0.21428571428571427,0.5484126984126985
|
| 536 |
-
aggregate,aggregate,HELM AirBench Operational Misuses,helm_airbench_240916.csv,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 537 |
-
aggregate,aggregate,HELM AirBench Operational Misuses,helm_airbench_240916.csv,kendall,random,8,1,-0.18184824186332696,0.5330356744917513
|
| 538 |
-
aggregate,aggregate,HELM AirBench Operational Misuses,helm_airbench_240916.csv,kendall,random,8,2,-0.42857142857142855,0.17886904761904762
|
| 539 |
-
aggregate,aggregate,HELM AirBench Violence & Extremism,helm_airbench_240916.csv,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 540 |
-
aggregate,aggregate,HELM AirBench Violence & Extremism,helm_airbench_240916.csv,kendall,random,8,1,-0.7142857142857142,0.014136904761904762
|
| 541 |
-
aggregate,aggregate,HELM AirBench Violence & Extremism,helm_airbench_240916.csv,kendall,random,8,2,-0.3571428571428571,0.27509920634920637
|
| 542 |
-
aggregate,aggregate,HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 543 |
-
aggregate,aggregate,HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,kendall,random,8,1,-0.7142857142857142,0.014136904761904762
|
| 544 |
-
aggregate,aggregate,HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,kendall,random,8,2,-0.2857142857142857,0.39875992063492066
|
| 545 |
-
aggregate,aggregate,HELM AirBench Sexual Content,helm_airbench_240916.csv,kendall,random,8,0,-0.42857142857142855,0.17886904761904762
|
| 546 |
-
aggregate,aggregate,HELM AirBench Sexual Content,helm_airbench_240916.csv,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 547 |
-
aggregate,aggregate,HELM AirBench Sexual Content,helm_airbench_240916.csv,kendall,random,8,2,-0.42857142857142855,0.17886904761904762
|
| 548 |
-
aggregate,aggregate,HELM AirBench Child Harm,helm_airbench_240916.csv,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 549 |
-
aggregate,aggregate,HELM AirBench Child Harm,helm_airbench_240916.csv,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 550 |
-
aggregate,aggregate,HELM AirBench Child Harm,helm_airbench_240916.csv,kendall,random,8,2,-0.42857142857142855,0.17886904761904762
|
| 551 |
-
aggregate,aggregate,HELM AirBench Self Harm,helm_airbench_240916.csv,kendall,random,8,0,-0.40006613209931935,0.17023995462900499
|
| 552 |
-
aggregate,aggregate,HELM AirBench Self Harm,helm_airbench_240916.csv,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 553 |
-
aggregate,aggregate,HELM AirBench Self Harm,helm_airbench_240916.csv,kendall,random,8,2,-0.40006613209931935,0.17023995462900499
|
| 554 |
-
aggregate,aggregate,HELM AirBench Political Usage,helm_airbench_240916.csv,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 555 |
-
aggregate,aggregate,HELM AirBench Political Usage,helm_airbench_240916.csv,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 556 |
-
aggregate,aggregate,HELM AirBench Political Usage,helm_airbench_240916.csv,kendall,random,8,2,-0.3571428571428571,0.27509920634920637
|
| 557 |
-
aggregate,aggregate,HELM AirBench Economic Harm,helm_airbench_240916.csv,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 558 |
-
aggregate,aggregate,HELM AirBench Economic Harm,helm_airbench_240916.csv,kendall,random,8,1,-0.6182840223353117,0.0340492747686748
|
| 559 |
-
aggregate,aggregate,HELM AirBench Economic Harm,helm_airbench_240916.csv,kendall,random,8,2,-0.3571428571428571,0.27509920634920637
|
| 560 |
-
aggregate,aggregate,HELM AirBench Deception,helm_airbench_240916.csv,kendall,random,8,0,-0.4999999999999999,0.10868055555555556
|
| 561 |
-
aggregate,aggregate,HELM AirBench Deception,helm_airbench_240916.csv,kendall,random,8,1,-0.6428571428571428,0.03115079365079365
|
| 562 |
-
aggregate,aggregate,HELM AirBench Deception,helm_airbench_240916.csv,kendall,random,8,2,-0.40006613209931935,0.17023995462900499
|
| 563 |
-
aggregate,aggregate,HELM AirBench Manipulation,helm_airbench_240916.csv,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 564 |
-
aggregate,aggregate,HELM AirBench Manipulation,helm_airbench_240916.csv,kendall,random,8,1,-0.6182840223353117,0.0340492747686748
|
| 565 |
-
aggregate,aggregate,HELM AirBench Manipulation,helm_airbench_240916.csv,kendall,random,8,2,-0.3571428571428571,0.27509920634920637
|
| 566 |
-
aggregate,aggregate,HELM AirBench Defamation,helm_airbench_240916.csv,kendall,random,8,0,-0.40006613209931935,0.17023995462900499
|
| 567 |
-
aggregate,aggregate,HELM AirBench Defamation,helm_airbench_240916.csv,kendall,random,8,1,-0.4999999999999999,0.10868055555555556
|
| 568 |
-
aggregate,aggregate,HELM AirBench Defamation,helm_airbench_240916.csv,kendall,random,8,2,-0.40006613209931935,0.17023995462900499
|
| 569 |
-
aggregate,aggregate,HELM AirBench Fundamental Rights,helm_airbench_240916.csv,kendall,random,8,0,-0.6182840223353117,0.0340492747686748
|
| 570 |
-
aggregate,aggregate,HELM AirBench Fundamental Rights,helm_airbench_240916.csv,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 571 |
-
aggregate,aggregate,HELM AirBench Fundamental Rights,helm_airbench_240916.csv,kendall,random,8,2,-0.41576092031014994,0.1612822677790775
|
| 572 |
-
aggregate,aggregate,HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 573 |
-
aggregate,aggregate,HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 574 |
-
aggregate,aggregate,HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,kendall,random,8,2,-0.4999999999999999,0.10868055555555556
|
| 575 |
-
aggregate,aggregate,HELM AirBench Privacy,helm_airbench_240916.csv,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 576 |
-
aggregate,aggregate,HELM AirBench Privacy,helm_airbench_240916.csv,kendall,random,8,1,-0.3571428571428571,0.27509920634920637
|
| 577 |
-
aggregate,aggregate,HELM AirBench Privacy,helm_airbench_240916.csv,kendall,random,8,2,-0.21428571428571427,0.5484126984126985
|
| 578 |
-
aggregate,aggregate,HELM AirBench Criminal Activities,helm_airbench_240916.csv,kendall,random,8,0,-0.5714285714285714,0.06101190476190476
|
| 579 |
-
aggregate,aggregate,HELM AirBench Criminal Activities,helm_airbench_240916.csv,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 580 |
-
aggregate,aggregate,HELM AirBench Criminal Activities,helm_airbench_240916.csv,kendall,random,8,2,-0.42857142857142855,0.17886904761904762
|
| 581 |
-
aggregate,aggregate,HELM AirBench AIR Score,helm_airbench_240916.csv,kendall,random,8,0,-0.6428571428571428,0.03115079365079365
|
| 582 |
-
aggregate,aggregate,HELM AirBench AIR Score,helm_airbench_240916.csv,kendall,random,8,1,-0.5714285714285714,0.06101190476190476
|
| 583 |
-
aggregate,aggregate,HELM AirBench AIR Score,helm_airbench_240916.csv,kendall,random,8,2,-0.47280542884465016,0.10506382347888965
|
| 584 |
-
aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 585 |
-
aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 586 |
-
aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 587 |
-
aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985
|
| 588 |
-
aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 589 |
-
aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 590 |
-
aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 591 |
-
aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 592 |
-
aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,2,-0.21428571428571427,0.5484126984126985
|
| 593 |
-
aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 594 |
-
aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 595 |
-
aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 596 |
-
aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 597 |
-
aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 598 |
-
aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,2,0.14285714285714285,0.7195436507936508
|
| 599 |
-
aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 600 |
-
aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,1,0.6910233190806425,0.017844011512848347
|
| 601 |
-
aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,2,0.40006613209931935,0.17023995462900499
|
| 602 |
-
aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 603 |
-
aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381
|
| 604 |
-
aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
|
| 605 |
-
aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 606 |
-
aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 607 |
-
aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,2,-0.14285714285714285,0.7195436507936508
|
| 608 |
-
aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,0,0.32732683535398854,0.2618277009271762
|
| 609 |
-
aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 610 |
-
aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,2,0.21428571428571427,0.5484126984126985
|
| 611 |
-
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 612 |
-
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 613 |
-
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 614 |
-
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 615 |
-
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,1,0.2545875386086578,0.38281014365989596
|
| 616 |
-
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 617 |
-
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 618 |
-
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 619 |
-
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 620 |
-
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 621 |
-
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 622 |
-
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 623 |
-
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 624 |
-
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 625 |
-
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,2,-0.07142857142857142,0.9048611111111111
|
| 626 |
-
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 627 |
-
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 628 |
-
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 629 |
-
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 630 |
-
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 631 |
-
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 632 |
-
aggregate,aggregate,Enkrypt AI Safety,enkrypt_ai_safety_240916.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 633 |
-
aggregate,aggregate,Enkrypt AI Safety,enkrypt_ai_safety_240916.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 634 |
-
aggregate,aggregate,Enkrypt AI Safety,enkrypt_ai_safety_240916.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 635 |
-
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 636 |
-
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 637 |
-
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 638 |
-
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
|
| 639 |
-
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 640 |
-
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
|
| 641 |
-
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 642 |
-
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 643 |
-
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
|
| 644 |
-
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 645 |
-
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 646 |
-
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 647 |
-
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 648 |
-
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 649 |
-
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 650 |
-
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 651 |
-
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 652 |
-
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 653 |
-
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 654 |
-
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 655 |
-
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 656 |
-
aggregate,aggregate,Decentralized Arena (0-1 Normalized),dec_arena_241022.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 657 |
-
aggregate,aggregate,Decentralized Arena (0-1 Normalized),dec_arena_241022.csv,kendall,random,8,1,0.40006613209931935,0.17023995462900499
|
| 658 |
-
aggregate,aggregate,Decentralized Arena (0-1 Normalized),dec_arena_241022.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 659 |
-
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 660 |
-
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 661 |
-
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,2,0.21428571428571427,0.5484126984126985
|
| 662 |
-
aggregate,aggregate,AgentBench,agenbench_240829.csv,kendall,random,8,0,0.32732683535398854,0.2618277009271762
|
| 663 |
-
aggregate,aggregate,AgentBench,agenbench_240829.csv,kendall,random,8,1,0.32732683535398854,0.2618277009271762
|
| 664 |
-
aggregate,aggregate,AgentBench,agenbench_240829.csv,kendall,random,8,2,0.32732683535398854,0.2618277009271762
|
| 665 |
-
aggregate,aggregate,MT-Bench,mtbench_240829_frozen.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 666 |
-
aggregate,aggregate,MT-Bench,mtbench_240829_frozen.csv,kendall,random,8,1,0.6182840223353117,0.0340492747686748
|
| 667 |
-
aggregate,aggregate,MT-Bench,mtbench_240829_frozen.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 668 |
-
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 669 |
-
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 670 |
-
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 671 |
-
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 672 |
-
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 673 |
-
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 674 |
-
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 675 |
-
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.0,1.0
|
| 676 |
-
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.14285714285714285,0.7195436507936508
|
| 677 |
-
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 678 |
-
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 679 |
-
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.21428571428571427,0.5484126984126985
|
| 680 |
-
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 681 |
-
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 682 |
-
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 683 |
-
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 684 |
-
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
|
| 685 |
-
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.0,1.0
|
| 686 |
-
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 687 |
-
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 688 |
-
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 689 |
-
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 690 |
-
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 691 |
-
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 692 |
-
aggregate,aggregate,eq_bench,eqbench_240912.csv,kendall,random,8,0,0.14285714285714285,0.7195436507936508
|
| 693 |
-
aggregate,aggregate,eq_bench,eqbench_240912.csv,kendall,random,8,1,0.07142857142857142,0.9048611111111111
|
| 694 |
-
aggregate,aggregate,eq_bench,eqbench_240912.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 695 |
-
aggregate,aggregate,magi_hard,eqbench_240912.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 696 |
-
aggregate,aggregate,magi_hard,eqbench_240912.csv,kendall,random,8,1,-0.07142857142857142,0.9048611111111111
|
| 697 |
-
aggregate,aggregate,magi_hard,eqbench_240912.csv,kendall,random,8,2,-0.07142857142857142,0.9048611111111111
|
| 698 |
-
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 699 |
-
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,1,-0.07142857142857142,0.9048611111111111
|
| 700 |
-
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 701 |
-
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 702 |
-
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,1,0.07142857142857142,0.9048611111111111
|
| 703 |
-
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 704 |
-
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,0,0.47280542884465016,0.10506382347888965
|
| 705 |
-
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,1,0.41576092031014994,0.1612822677790775
|
| 706 |
-
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762
|
| 707 |
-
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 708 |
-
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 709 |
-
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 710 |
-
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 711 |
-
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,1,-0.21428571428571427,0.5484126984126985
|
| 712 |
-
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 713 |
-
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,0,0.6425396041156862,0.030400749685896046
|
| 714 |
-
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,1,-0.036369648372665396,0.9007802600472398
|
| 715 |
-
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 716 |
-
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 717 |
-
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,1,0.21428571428571427,0.5484126984126985
|
| 718 |
-
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,2,0.47280542884465016,0.10506382347888965
|
| 719 |
-
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 720 |
-
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,1,0.14285714285714285,0.7195436507936508
|
| 721 |
-
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 722 |
-
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 723 |
-
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,1,0.14285714285714285,0.7195436507936508
|
| 724 |
-
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 725 |
-
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111
|
| 726 |
-
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,1,0.47280542884465016,0.10506382347888965
|
| 727 |
-
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 728 |
-
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 729 |
-
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 730 |
-
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 731 |
-
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 732 |
-
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 733 |
-
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,2,0.7637626158259734,0.008839740160738534
|
| 734 |
-
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 735 |
-
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 736 |
-
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 737 |
-
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 738 |
-
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 739 |
-
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
|
| 740 |
-
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 741 |
-
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 742 |
-
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 743 |
-
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
|
| 744 |
-
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762
|
| 745 |
-
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 746 |
-
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 747 |
-
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 748 |
-
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 749 |
-
aggregate,aggregate,hydrox_integrity,hydrox_safety_241001.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 750 |
-
aggregate,aggregate,hydrox_integrity,hydrox_safety_241001.csv,kendall,random,8,1,0.0,1.0
|
| 751 |
-
aggregate,aggregate,hydrox_integrity,hydrox_safety_241001.csv,kendall,random,8,2,0.14285714285714285,0.7195436507936508
|
| 752 |
-
aggregate,aggregate,hydrox_overall_score,hydrox_safety_241001.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 753 |
-
aggregate,aggregate,hydrox_overall_score,hydrox_safety_241001.csv,kendall,random,8,1,0.0,1.0
|
| 754 |
-
aggregate,aggregate,hydrox_overall_score,hydrox_safety_241001.csv,kendall,random,8,2,0.14285714285714285,0.7195436507936508
|
| 755 |
-
aggregate,aggregate,hydrox_privacy,hydrox_safety_241001.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 756 |
-
aggregate,aggregate,hydrox_privacy,hydrox_safety_241001.csv,kendall,random,8,1,-0.07142857142857142,0.9048611111111111
|
| 757 |
-
aggregate,aggregate,hydrox_privacy,hydrox_safety_241001.csv,kendall,random,8,2,0.14285714285714285,0.7195436507936508
|
| 758 |
-
aggregate,aggregate,hydrox_safety,hydrox_safety_241001.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 759 |
-
aggregate,aggregate,hydrox_safety,hydrox_safety_241001.csv,kendall,random,8,1,-0.07142857142857142,0.9048611111111111
|
| 760 |
-
aggregate,aggregate,hydrox_safety,hydrox_safety_241001.csv,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
| 761 |
-
aggregate,aggregate,hydrox_security,hydrox_safety_241001.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 762 |
-
aggregate,aggregate,hydrox_security,hydrox_safety_241001.csv,kendall,random,8,1,0.0,1.0
|
| 763 |
-
aggregate,aggregate,hydrox_security,hydrox_safety_241001.csv,kendall,random,8,2,0.07142857142857142,0.9048611111111111
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cache/agreements_cache_5e66a88dab42480065db47711c55c458.csv
CHANGED
|
@@ -155,57 +155,57 @@ MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.74
|
|
| 155 |
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 156 |
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 157 |
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
|
| 158 |
-
HELM AirBench Security Risks,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 159 |
-
HELM AirBench Security Risks,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 160 |
-
HELM AirBench Security Risks,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 161 |
-
HELM AirBench Operational Misuses,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 162 |
-
HELM AirBench Operational Misuses,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 163 |
-
HELM AirBench Operational Misuses,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 164 |
-
HELM AirBench Violence & Extremism,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 165 |
-
HELM AirBench Violence & Extremism,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 166 |
-
HELM AirBench Violence & Extremism,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 167 |
-
HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 168 |
-
HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 169 |
-
HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 170 |
-
HELM AirBench Sexual Content,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 171 |
-
HELM AirBench Sexual Content,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 172 |
-
HELM AirBench Sexual Content,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 173 |
-
HELM AirBench Child Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 174 |
-
HELM AirBench Child Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 175 |
-
HELM AirBench Child Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 176 |
-
HELM AirBench Self Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 177 |
-
HELM AirBench Self Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 178 |
-
HELM AirBench Self Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 179 |
-
HELM AirBench Political Usage,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 180 |
-
HELM AirBench Political Usage,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 181 |
-
HELM AirBench Political Usage,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 182 |
-
HELM AirBench Economic Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 183 |
-
HELM AirBench Economic Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 184 |
-
HELM AirBench Economic Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 185 |
-
HELM AirBench Deception,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 186 |
-
HELM AirBench Deception,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 187 |
-
HELM AirBench Deception,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 188 |
-
HELM AirBench Manipulation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 189 |
-
HELM AirBench Manipulation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 190 |
-
HELM AirBench Manipulation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 191 |
-
HELM AirBench Defamation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 192 |
-
HELM AirBench Defamation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 193 |
-
HELM AirBench Defamation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 194 |
-
HELM AirBench Fundamental Rights,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 195 |
-
HELM AirBench Fundamental Rights,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 196 |
-
HELM AirBench Fundamental Rights,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 197 |
-
HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 198 |
-
HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 199 |
-
HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 200 |
-
HELM AirBench Privacy,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 201 |
-
HELM AirBench Privacy,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 202 |
-
HELM AirBench Privacy,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 203 |
-
HELM AirBench Criminal Activities,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 204 |
-
HELM AirBench Criminal Activities,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 205 |
-
HELM AirBench Criminal Activities,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 206 |
-
HELM AirBench AIR Score,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0
|
| 207 |
-
HELM AirBench AIR Score,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1
|
| 208 |
-
HELM AirBench AIR Score,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2
|
| 209 |
OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968
|
| 210 |
OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 211 |
OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
|
@@ -365,21 +365,21 @@ LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,rand
|
|
| 365 |
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 366 |
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 367 |
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 368 |
-
|
| 369 |
-
|
| 370 |
-
|
| 371 |
-
|
| 372 |
-
|
| 373 |
-
|
| 374 |
-
|
| 375 |
-
|
| 376 |
-
|
| 377 |
-
|
| 378 |
-
|
| 379 |
-
|
| 380 |
-
|
| 381 |
-
|
| 382 |
-
|
| 383 |
aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985
|
| 384 |
aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 385 |
aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
|
@@ -536,57 +536,57 @@ aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,2,0.74
|
|
| 536 |
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 537 |
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 538 |
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
|
| 539 |
-
aggregate,aggregate,HELM AirBench Security Risks,helm_airbench_240916.csv,kendall,random,8,0
|
| 540 |
-
aggregate,aggregate,HELM AirBench Security Risks,helm_airbench_240916.csv,kendall,random,8,1
|
| 541 |
-
aggregate,aggregate,HELM AirBench Security Risks,helm_airbench_240916.csv,kendall,random,8,2
|
| 542 |
-
aggregate,aggregate,HELM AirBench Operational Misuses,helm_airbench_240916.csv,kendall,random,8,0
|
| 543 |
-
aggregate,aggregate,HELM AirBench Operational Misuses,helm_airbench_240916.csv,kendall,random,8,1
|
| 544 |
-
aggregate,aggregate,HELM AirBench Operational Misuses,helm_airbench_240916.csv,kendall,random,8,2
|
| 545 |
-
aggregate,aggregate,HELM AirBench Violence & Extremism,helm_airbench_240916.csv,kendall,random,8,0
|
| 546 |
-
aggregate,aggregate,HELM AirBench Violence & Extremism,helm_airbench_240916.csv,kendall,random,8,1
|
| 547 |
-
aggregate,aggregate,HELM AirBench Violence & Extremism,helm_airbench_240916.csv,kendall,random,8,2
|
| 548 |
-
aggregate,aggregate,HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,kendall,random,8,0
|
| 549 |
-
aggregate,aggregate,HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,kendall,random,8,1
|
| 550 |
-
aggregate,aggregate,HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,kendall,random,8,2
|
| 551 |
-
aggregate,aggregate,HELM AirBench Sexual Content,helm_airbench_240916.csv,kendall,random,8,0
|
| 552 |
-
aggregate,aggregate,HELM AirBench Sexual Content,helm_airbench_240916.csv,kendall,random,8,1
|
| 553 |
-
aggregate,aggregate,HELM AirBench Sexual Content,helm_airbench_240916.csv,kendall,random,8,2
|
| 554 |
-
aggregate,aggregate,HELM AirBench Child Harm,helm_airbench_240916.csv,kendall,random,8,0
|
| 555 |
-
aggregate,aggregate,HELM AirBench Child Harm,helm_airbench_240916.csv,kendall,random,8,1
|
| 556 |
-
aggregate,aggregate,HELM AirBench Child Harm,helm_airbench_240916.csv,kendall,random,8,2
|
| 557 |
-
aggregate,aggregate,HELM AirBench Self Harm,helm_airbench_240916.csv,kendall,random,8,0
|
| 558 |
-
aggregate,aggregate,HELM AirBench Self Harm,helm_airbench_240916.csv,kendall,random,8,1
|
| 559 |
-
aggregate,aggregate,HELM AirBench Self Harm,helm_airbench_240916.csv,kendall,random,8,2
|
| 560 |
-
aggregate,aggregate,HELM AirBench Political Usage,helm_airbench_240916.csv,kendall,random,8,0
|
| 561 |
-
aggregate,aggregate,HELM AirBench Political Usage,helm_airbench_240916.csv,kendall,random,8,1
|
| 562 |
-
aggregate,aggregate,HELM AirBench Political Usage,helm_airbench_240916.csv,kendall,random,8,2
|
| 563 |
-
aggregate,aggregate,HELM AirBench Economic Harm,helm_airbench_240916.csv,kendall,random,8,0
|
| 564 |
-
aggregate,aggregate,HELM AirBench Economic Harm,helm_airbench_240916.csv,kendall,random,8,1
|
| 565 |
-
aggregate,aggregate,HELM AirBench Economic Harm,helm_airbench_240916.csv,kendall,random,8,2
|
| 566 |
-
aggregate,aggregate,HELM AirBench Deception,helm_airbench_240916.csv,kendall,random,8,0
|
| 567 |
-
aggregate,aggregate,HELM AirBench Deception,helm_airbench_240916.csv,kendall,random,8,1
|
| 568 |
-
aggregate,aggregate,HELM AirBench Deception,helm_airbench_240916.csv,kendall,random,8,2
|
| 569 |
-
aggregate,aggregate,HELM AirBench Manipulation,helm_airbench_240916.csv,kendall,random,8,0
|
| 570 |
-
aggregate,aggregate,HELM AirBench Manipulation,helm_airbench_240916.csv,kendall,random,8,1
|
| 571 |
-
aggregate,aggregate,HELM AirBench Manipulation,helm_airbench_240916.csv,kendall,random,8,2
|
| 572 |
-
aggregate,aggregate,HELM AirBench Defamation,helm_airbench_240916.csv,kendall,random,8,0
|
| 573 |
-
aggregate,aggregate,HELM AirBench Defamation,helm_airbench_240916.csv,kendall,random,8,1
|
| 574 |
-
aggregate,aggregate,HELM AirBench Defamation,helm_airbench_240916.csv,kendall,random,8,2
|
| 575 |
-
aggregate,aggregate,HELM AirBench Fundamental Rights,helm_airbench_240916.csv,kendall,random,8,0
|
| 576 |
-
aggregate,aggregate,HELM AirBench Fundamental Rights,helm_airbench_240916.csv,kendall,random,8,1
|
| 577 |
-
aggregate,aggregate,HELM AirBench Fundamental Rights,helm_airbench_240916.csv,kendall,random,8,2
|
| 578 |
-
aggregate,aggregate,HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,kendall,random,8,0
|
| 579 |
-
aggregate,aggregate,HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,kendall,random,8,1
|
| 580 |
-
aggregate,aggregate,HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,kendall,random,8,2
|
| 581 |
-
aggregate,aggregate,HELM AirBench Privacy,helm_airbench_240916.csv,kendall,random,8,0
|
| 582 |
-
aggregate,aggregate,HELM AirBench Privacy,helm_airbench_240916.csv,kendall,random,8,1
|
| 583 |
-
aggregate,aggregate,HELM AirBench Privacy,helm_airbench_240916.csv,kendall,random,8,2
|
| 584 |
-
aggregate,aggregate,HELM AirBench Criminal Activities,helm_airbench_240916.csv,kendall,random,8,0
|
| 585 |
-
aggregate,aggregate,HELM AirBench Criminal Activities,helm_airbench_240916.csv,kendall,random,8,1
|
| 586 |
-
aggregate,aggregate,HELM AirBench Criminal Activities,helm_airbench_240916.csv,kendall,random,8,2
|
| 587 |
-
aggregate,aggregate,HELM AirBench AIR Score,helm_airbench_240916.csv,kendall,random,8,0
|
| 588 |
-
aggregate,aggregate,HELM AirBench AIR Score,helm_airbench_240916.csv,kendall,random,8,1
|
| 589 |
-
aggregate,aggregate,HELM AirBench AIR Score,helm_airbench_240916.csv,kendall,random,8,2
|
| 590 |
aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968
|
| 591 |
aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 592 |
aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
|
@@ -746,18 +746,18 @@ aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,rand
|
|
| 746 |
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 747 |
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 748 |
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 749 |
-
aggregate,aggregate,
|
| 750 |
-
aggregate,aggregate,
|
| 751 |
-
aggregate,aggregate,
|
| 752 |
-
aggregate,aggregate,
|
| 753 |
-
aggregate,aggregate,
|
| 754 |
-
aggregate,aggregate,
|
| 755 |
-
aggregate,aggregate,
|
| 756 |
-
aggregate,aggregate,
|
| 757 |
-
aggregate,aggregate,
|
| 758 |
-
aggregate,aggregate,
|
| 759 |
-
aggregate,aggregate,
|
| 760 |
-
aggregate,aggregate,
|
| 761 |
-
aggregate,aggregate,
|
| 762 |
-
aggregate,aggregate,
|
| 763 |
-
aggregate,aggregate,
|
|
|
|
| 155 |
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 156 |
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 157 |
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
|
| 158 |
+
HELM AirBench Security Risks,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 159 |
+
HELM AirBench Security Risks,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 160 |
+
HELM AirBench Security Risks,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 161 |
+
HELM AirBench Operational Misuses,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 162 |
+
HELM AirBench Operational Misuses,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 163 |
+
HELM AirBench Operational Misuses,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 164 |
+
HELM AirBench Violence & Extremism,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 165 |
+
HELM AirBench Violence & Extremism,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 166 |
+
HELM AirBench Violence & Extremism,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 167 |
+
HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.2857142857142857,0.39875992063492066
|
| 168 |
+
HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 169 |
+
HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 170 |
+
HELM AirBench Sexual Content,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.2857142857142857,0.39875992063492066
|
| 171 |
+
HELM AirBench Sexual Content,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 172 |
+
HELM AirBench Sexual Content,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 173 |
+
HELM AirBench Child Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 174 |
+
HELM AirBench Child Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 175 |
+
HELM AirBench Child Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 176 |
+
HELM AirBench Self Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.32732683535398854,0.2618277009271762
|
| 177 |
+
HELM AirBench Self Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762
|
| 178 |
+
HELM AirBench Self Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 179 |
+
HELM AirBench Political Usage,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 180 |
+
HELM AirBench Political Usage,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 181 |
+
HELM AirBench Political Usage,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 182 |
+
HELM AirBench Economic Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 183 |
+
HELM AirBench Economic Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 184 |
+
HELM AirBench Economic Harm,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 185 |
+
HELM AirBench Deception,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.47280542884465016,0.10506382347888965
|
| 186 |
+
HELM AirBench Deception,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762
|
| 187 |
+
HELM AirBench Deception,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 188 |
+
HELM AirBench Manipulation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 189 |
+
HELM AirBench Manipulation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 190 |
+
HELM AirBench Manipulation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.6182840223353117,0.0340492747686748
|
| 191 |
+
HELM AirBench Defamation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.40006613209931935,0.17023995462900499
|
| 192 |
+
HELM AirBench Defamation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 193 |
+
HELM AirBench Defamation,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.40006613209931935,0.17023995462900499
|
| 194 |
+
HELM AirBench Fundamental Rights,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.40006613209931935,0.17023995462900499
|
| 195 |
+
HELM AirBench Fundamental Rights,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 196 |
+
HELM AirBench Fundamental Rights,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.6182840223353117,0.0340492747686748
|
| 197 |
+
HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 198 |
+
HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.5455447255899809,0.0614649096074132
|
| 199 |
+
HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.47280542884465016,0.10506382347888965
|
| 200 |
+
HELM AirBench Privacy,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 201 |
+
HELM AirBench Privacy,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 202 |
+
HELM AirBench Privacy,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 203 |
+
HELM AirBench Criminal Activities,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 204 |
+
HELM AirBench Criminal Activities,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 205 |
+
HELM AirBench Criminal Activities,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 206 |
+
HELM AirBench AIR Score,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 207 |
+
HELM AirBench AIR Score,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 208 |
+
HELM AirBench AIR Score,helm_airbench_240916.csv,aggregate,aggregate,kendall,random,8,2,0.5455447255899809,0.0614649096074132
|
| 209 |
OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968
|
| 210 |
OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 211 |
OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
|
|
|
| 365 |
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 366 |
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 367 |
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 368 |
+
Hydrox Integrity,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,0,0.07142857142857142,0.9048611111111111
|
| 369 |
+
Hydrox Integrity,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 370 |
+
Hydrox Integrity,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 371 |
+
Hydrox Overall Score,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,0,0.0,1.0
|
| 372 |
+
Hydrox Overall Score,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 373 |
+
Hydrox Overall Score,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 374 |
+
Hydrox Privacy,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,0,0.0,1.0
|
| 375 |
+
Hydrox Privacy,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 376 |
+
Hydrox Privacy,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,2,0.21428571428571427,0.5484126984126985
|
| 377 |
+
Hydrox Safety,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,0,-0.07142857142857142,0.9048611111111111
|
| 378 |
+
Hydrox Safety,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 379 |
+
Hydrox Safety,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 380 |
+
Hydrox Security,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,0,0.07142857142857142,0.9048611111111111
|
| 381 |
+
Hydrox Security,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 382 |
+
Hydrox Security,hydrox_safety_241001.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 383 |
aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985
|
| 384 |
aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 385 |
aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
|
|
|
| 536 |
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
|
| 537 |
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 538 |
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
|
| 539 |
+
aggregate,aggregate,HELM AirBench Security Risks,helm_airbench_240916.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 540 |
+
aggregate,aggregate,HELM AirBench Security Risks,helm_airbench_240916.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 541 |
+
aggregate,aggregate,HELM AirBench Security Risks,helm_airbench_240916.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
|
| 542 |
+
aggregate,aggregate,HELM AirBench Operational Misuses,helm_airbench_240916.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 543 |
+
aggregate,aggregate,HELM AirBench Operational Misuses,helm_airbench_240916.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 544 |
+
aggregate,aggregate,HELM AirBench Operational Misuses,helm_airbench_240916.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 545 |
+
aggregate,aggregate,HELM AirBench Violence & Extremism,helm_airbench_240916.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 546 |
+
aggregate,aggregate,HELM AirBench Violence & Extremism,helm_airbench_240916.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 547 |
+
aggregate,aggregate,HELM AirBench Violence & Extremism,helm_airbench_240916.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 548 |
+
aggregate,aggregate,HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,kendall,random,8,0,0.2857142857142857,0.39875992063492066
|
| 549 |
+
aggregate,aggregate,HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 550 |
+
aggregate,aggregate,HELM AirBench Hate/Toxicity,helm_airbench_240916.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 551 |
+
aggregate,aggregate,HELM AirBench Sexual Content,helm_airbench_240916.csv,kendall,random,8,0,0.2857142857142857,0.39875992063492066
|
| 552 |
+
aggregate,aggregate,HELM AirBench Sexual Content,helm_airbench_240916.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 553 |
+
aggregate,aggregate,HELM AirBench Sexual Content,helm_airbench_240916.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 554 |
+
aggregate,aggregate,HELM AirBench Child Harm,helm_airbench_240916.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 555 |
+
aggregate,aggregate,HELM AirBench Child Harm,helm_airbench_240916.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 556 |
+
aggregate,aggregate,HELM AirBench Child Harm,helm_airbench_240916.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 557 |
+
aggregate,aggregate,HELM AirBench Self Harm,helm_airbench_240916.csv,kendall,random,8,0,0.32732683535398854,0.2618277009271762
|
| 558 |
+
aggregate,aggregate,HELM AirBench Self Harm,helm_airbench_240916.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762
|
| 559 |
+
aggregate,aggregate,HELM AirBench Self Harm,helm_airbench_240916.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
|
| 560 |
+
aggregate,aggregate,HELM AirBench Political Usage,helm_airbench_240916.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 561 |
+
aggregate,aggregate,HELM AirBench Political Usage,helm_airbench_240916.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 562 |
+
aggregate,aggregate,HELM AirBench Political Usage,helm_airbench_240916.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 563 |
+
aggregate,aggregate,HELM AirBench Economic Harm,helm_airbench_240916.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 564 |
+
aggregate,aggregate,HELM AirBench Economic Harm,helm_airbench_240916.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 565 |
+
aggregate,aggregate,HELM AirBench Economic Harm,helm_airbench_240916.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 566 |
+
aggregate,aggregate,HELM AirBench Deception,helm_airbench_240916.csv,kendall,random,8,0,0.47280542884465016,0.10506382347888965
|
| 567 |
+
aggregate,aggregate,HELM AirBench Deception,helm_airbench_240916.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762
|
| 568 |
+
aggregate,aggregate,HELM AirBench Deception,helm_airbench_240916.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 569 |
+
aggregate,aggregate,HELM AirBench Manipulation,helm_airbench_240916.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 570 |
+
aggregate,aggregate,HELM AirBench Manipulation,helm_airbench_240916.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 571 |
+
aggregate,aggregate,HELM AirBench Manipulation,helm_airbench_240916.csv,kendall,random,8,2,0.6182840223353117,0.0340492747686748
|
| 572 |
+
aggregate,aggregate,HELM AirBench Defamation,helm_airbench_240916.csv,kendall,random,8,0,0.40006613209931935,0.17023995462900499
|
| 573 |
+
aggregate,aggregate,HELM AirBench Defamation,helm_airbench_240916.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 574 |
+
aggregate,aggregate,HELM AirBench Defamation,helm_airbench_240916.csv,kendall,random,8,2,0.40006613209931935,0.17023995462900499
|
| 575 |
+
aggregate,aggregate,HELM AirBench Fundamental Rights,helm_airbench_240916.csv,kendall,random,8,0,0.40006613209931935,0.17023995462900499
|
| 576 |
+
aggregate,aggregate,HELM AirBench Fundamental Rights,helm_airbench_240916.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 577 |
+
aggregate,aggregate,HELM AirBench Fundamental Rights,helm_airbench_240916.csv,kendall,random,8,2,0.6182840223353117,0.0340492747686748
|
| 578 |
+
aggregate,aggregate,HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 579 |
+
aggregate,aggregate,HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,kendall,random,8,1,0.5455447255899809,0.0614649096074132
|
| 580 |
+
aggregate,aggregate,HELM AirBench Discrimination/Bias,helm_airbench_240916.csv,kendall,random,8,2,0.47280542884465016,0.10506382347888965
|
| 581 |
+
aggregate,aggregate,HELM AirBench Privacy,helm_airbench_240916.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637
|
| 582 |
+
aggregate,aggregate,HELM AirBench Privacy,helm_airbench_240916.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
|
| 583 |
+
aggregate,aggregate,HELM AirBench Privacy,helm_airbench_240916.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
|
| 584 |
+
aggregate,aggregate,HELM AirBench Criminal Activities,helm_airbench_240916.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
|
| 585 |
+
aggregate,aggregate,HELM AirBench Criminal Activities,helm_airbench_240916.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 586 |
+
aggregate,aggregate,HELM AirBench Criminal Activities,helm_airbench_240916.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 587 |
+
aggregate,aggregate,HELM AirBench AIR Score,helm_airbench_240916.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
|
| 588 |
+
aggregate,aggregate,HELM AirBench AIR Score,helm_airbench_240916.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 589 |
+
aggregate,aggregate,HELM AirBench AIR Score,helm_airbench_240916.csv,kendall,random,8,2,0.5455447255899809,0.0614649096074132
|
| 590 |
aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968
|
| 591 |
aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
|
| 592 |
aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
|
|
|
| 746 |
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
|
| 747 |
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
|
| 748 |
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
|
| 749 |
+
aggregate,aggregate,Hydrox Integrity,hydrox_safety_241001.csv,kendall,random,8,0,0.07142857142857142,0.9048611111111111
|
| 750 |
+
aggregate,aggregate,Hydrox Integrity,hydrox_safety_241001.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 751 |
+
aggregate,aggregate,Hydrox Integrity,hydrox_safety_241001.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 752 |
+
aggregate,aggregate,Hydrox Overall Score,hydrox_safety_241001.csv,kendall,random,8,0,0.0,1.0
|
| 753 |
+
aggregate,aggregate,Hydrox Overall Score,hydrox_safety_241001.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 754 |
+
aggregate,aggregate,Hydrox Overall Score,hydrox_safety_241001.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 755 |
+
aggregate,aggregate,Hydrox Privacy,hydrox_safety_241001.csv,kendall,random,8,0,0.0,1.0
|
| 756 |
+
aggregate,aggregate,Hydrox Privacy,hydrox_safety_241001.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 757 |
+
aggregate,aggregate,Hydrox Privacy,hydrox_safety_241001.csv,kendall,random,8,2,0.21428571428571427,0.5484126984126985
|
| 758 |
+
aggregate,aggregate,Hydrox Safety,hydrox_safety_241001.csv,kendall,random,8,0,-0.07142857142857142,0.9048611111111111
|
| 759 |
+
aggregate,aggregate,Hydrox Safety,hydrox_safety_241001.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
|
| 760 |
+
aggregate,aggregate,Hydrox Safety,hydrox_safety_241001.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
| 761 |
+
aggregate,aggregate,Hydrox Security,hydrox_safety_241001.csv,kendall,random,8,0,0.07142857142857142,0.9048611111111111
|
| 762 |
+
aggregate,aggregate,Hydrox Security,hydrox_safety_241001.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
|
| 763 |
+
aggregate,aggregate,Hydrox Security,hydrox_safety_241001.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066
|
cache/allbenchs_cache_05c0405c5253dda90dc632e052accfd2.csv
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cache/allbenchs_cache_5e66a88dab42480065db47711c55c458.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|