Upload folder using huggingface_hub

results/cross_lingual/zero_shot/cross_logiqa.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.4496753246753246,0.49188311688311687,0.46
 Meta-Llama-3-8B-Instruct,0.4610389610389611,0.45097402597402597,0.4559509553669637,0.5965909090909091,0.48295454545454547,0.5,0.4602272727272727,0.42045454545454547,0.4034090909090909,0.36363636363636365
 Meta-Llama-3.1-70B-Instruct,0.6566558441558442,0.598051948051948,0.6259852839118454,0.7443181818181818,0.7215909090909091,0.6647727272727273,0.6534090909090909,0.6193181818181818,0.625,0.5681818181818182
 Qwen2_5_3B_Instruct,0.4878246753246754,0.3594155844155844,0.41388918606681485,0.6079545454545454,0.6420454545454546,0.45454545454545453,0.4602272727272727,0.48295454545454547,0.42045454545454547,0.3465909090909091
+cross_openhermes_llama3_70b_4096_inst_2,0.6542207792207791,0.5862012987012987,0.618346089144296,0.7329545454545454,0.7045454545454546,0.6477272727272727,0.6420454545454546,0.625,0.6647727272727273,0.5625
 SeaLLMs-v3-7B-Chat,0.5551948051948051,0.5142857142857142,0.5339578453833284,0.6022727272727273,0.6647727272727273,0.5738636363636364,0.5454545454545454,0.5170454545454546,0.5,0.48295454545454547
 Qwen2_5_72B_Instruct,0.7248376623376623,0.6852272727272727,0.7044761161663122,0.8011363636363636,0.7954545454545454,0.7272727272727273,0.6704545454545454,0.7159090909090909,0.7159090909090909,0.6477272727272727
 gemma-2-9b-it,0.6185064935064934,0.5592532467532466,0.5873893507784849,0.6647727272727273,0.6761363636363636,0.5625,0.6193181818181818,0.5795454545454546,0.6420454545454546,0.5852272727272727

results/cross_lingual/zero_shot/cross_mmlu.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.5523809523809523,0.5384761904761904,0.545
 Meta-Llama-3-8B-Instruct,0.5733333333333334,0.4742857142857144,0.5191272726777197,0.7133333333333334,0.5866666666666667,0.5733333333333334,0.5866666666666667,0.5066666666666667,0.5333333333333333,0.5133333333333333
 Meta-Llama-3.1-70B-Instruct,0.7638095238095238,0.7716190476190474,0.7676944251955988,0.8,0.74,0.7666666666666667,0.7666666666666667,0.76,0.7666666666666667,0.7466666666666667
 Qwen2_5_3B_Instruct,0.5857142857142856,0.48952380952380964,0.533316462053399,0.6933333333333334,0.6666666666666666,0.64,0.5266666666666666,0.6333333333333333,0.5466666666666666,0.3933333333333333
+cross_openhermes_llama3_70b_4096_inst_2,0.7466666666666667,0.7828571428571428,0.7643337483933655,0.8,0.72,0.7333333333333333,0.72,0.7866666666666666,0.7466666666666667,0.72
 SeaLLMs-v3-7B-Chat,0.6628571428571429,0.6135238095238095,0.6372370860992635,0.74,0.6933333333333334,0.6933333333333334,0.6466666666666666,0.68,0.6,0.5866666666666667
 Qwen2_5_72B_Instruct,0.8123809523809525,0.8140952380952383,0.8132371917701643,0.8533333333333334,0.8333333333333334,0.84,0.7933333333333333,0.8066666666666666,0.7733333333333333,0.7866666666666666
 gemma-2-9b-it,0.7161904761904762,0.7163809523809525,0.7162857015727578,0.7733333333333333,0.74,0.7066666666666667,0.64,0.7266666666666667,0.6933333333333334,0.7333333333333333

results/cross_lingual/zero_shot/cross_xquad.csv

@@ -8,6 +8,7 @@ cross_openhermes_llama3_8b_4096_inst,0.9052521008403361,0.8705882352941177,0.887
 Meta-Llama-3-8B-Instruct,0.9210084033613445,0.880672268907563,0.9003888121913395,0.9411764705882353,0.9033613445378151,0.9260504201680673,0.9134453781512605,,,
 Meta-Llama-3.1-70B-Instruct,0.9615546218487395,0.9512605042016806,0.9563798632627071,0.9647058823529412,0.9512605042016806,0.9647058823529412,0.965546218487395,,,
 Qwen2_5_3B_Instruct,0.9378151260504202,0.8924369747899159,0.9145635113049859,0.9504201680672268,0.9327731092436975,0.9378151260504202,0.9302521008403362,,,
+cross_openhermes_llama3_70b_4096_inst_2,0.959873949579832,0.9579831932773109,0.9589276393593623,0.965546218487395,0.9554621848739496,0.9621848739495799,0.9563025210084034,,,
 SeaLLMs-v3-7B-Chat,0.9403361344537815,0.917016806722689,0.9285300818164836,0.9537815126050421,0.9378151260504202,0.9394957983193277,0.9302521008403362,,,
 Qwen2_5_72B_Instruct,0.9682773109243697,0.9632352941176471,0.9657497216354985,0.9714285714285714,0.9638655462184874,0.9680672268907563,0.9697478991596639,,,
 gemma-2-9b-it,0.9567226890756303,0.9350840336134454,0.9457796088507574,0.9663865546218487,0.9411764705882353,0.9588235294117647,0.9605042016806723,,,

results/cultural_reasoning/zero_shot/cn_eval.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.47619047619047616
 Meta-Llama-3-8B-Instruct,0.4666666666666667
 Meta-Llama-3.1-70B-Instruct,0.5428571428571428
 Qwen2_5_3B_Instruct,0.7142857142857143
+cross_openhermes_llama3_70b_4096_inst_2,0.638095238095238
 SeaLLMs-v3-7B-Chat,0.819047619047619
 Qwen2_5_72B_Instruct,0.8761904761904762
 gemma-2-9b-it,0.580952380952381

results/cultural_reasoning/zero_shot/ph_eval.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.47
 Meta-Llama-3-8B-Instruct,0.58
 Meta-Llama-3.1-70B-Instruct,0.68
 Qwen2_5_3B_Instruct,0.4
+cross_openhermes_llama3_70b_4096_inst_2,0.66
 SeaLLMs-v3-7B-Chat,0.47
 Qwen2_5_72B_Instruct,0.72
 gemma-2-9b-it,0.58

results/cultural_reasoning/zero_shot/sg_eval.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.6019417475728155
 Meta-Llama-3-8B-Instruct,0.6504854368932039
 Meta-Llama-3.1-70B-Instruct,0.7184466019417476
 Qwen2_5_3B_Instruct,0.6310679611650486
+cross_openhermes_llama3_70b_4096_inst_2,0.7087378640776699
 SeaLLMs-v3-7B-Chat,0.7184466019417476
 Qwen2_5_72B_Instruct,0.7669902912621359
 gemma-2-9b-it,0.6699029126213593

results/cultural_reasoning/zero_shot/sg_eval_v1_cleaned.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.6029411764705882
 Meta-Llama-3-8B-Instruct,0.5882352941176471
 Meta-Llama-3.1-70B-Instruct,0.6617647058823529
 Qwen2_5_3B_Instruct,0.5882352941176471
+cross_openhermes_llama3_70b_4096_inst_2,0.6470588235294118
 SeaLLMs-v3-7B-Chat,0.5882352941176471
 Qwen2_5_72B_Instruct,0.7205882352941176
 gemma-2-9b-it,0.6029411764705882
@@ -16,7 +17,7 @@ Meta-Llama-3-70B-Instruct,0.6617647058823529
 Qwen2_5_14B_Instruct,0.6911764705882353
 sg_llama3_8192_8b,0.47058823529411764
 sg_llama3_70b_inst,0.6176470588235294
-gemma-2-2b-it,0.4852941176470588
+gemma-2-2b-it,0.5147058823529411
 llama3-8b-cpt-sea-lionv2-instruct,0.6617647058823529
 Qwen2_5_0_5B_Instruct,0.36764705882352944
 GPT4o_0513,0.8088235294117647

results/cultural_reasoning/zero_shot/sg_eval_v2_mcq.csv

@@ -1,9 +1,11 @@
 Model,Accuracy
+Meta-Llama-3.1-8B-Instruct,0.7854545454545454
 Qwen2_5_32B_Instruct,0.8436363636363636
 Qwen2_5_7B_Instruct,0.78
 Qwen2_5_1_5B_Instruct,0.6636363636363637
 cross_openhermes_llama3_8b_4096_inst,0.7490909090909091
 Qwen2_5_3B_Instruct,0.72
+cross_openhermes_llama3_70b_4096_inst_2,0.8618181818181818
 Qwen2_5_72B_Instruct,0.8618181818181818
 Meta-Llama-3-70B-Instruct,0.8381818181818181
 Qwen2_5_14B_Instruct,0.8345454545454546

results/cultural_reasoning/zero_shot/sg_eval_v2_open.csv

@@ -1,14 +1,17 @@
 Model,Accuracy
+Meta-Llama-3.1-8B-Instruct,49.2
 Qwen2_5_32B_Instruct,53.2
 Qwen2_5_7B_Instruct,50.279999999999994
 Qwen2_5_1_5B_Instruct,44.480000000000004
 cross_openhermes_llama3_8b_4096_inst,51.6
 Qwen2_5_3B_Instruct,47.24
+cross_openhermes_llama3_70b_4096_inst_2,55.8
 Qwen2_5_72B_Instruct,53.32
 Meta-Llama-3-70B-Instruct,50.599999999999994
 Qwen2_5_14B_Instruct,53.2
 sg_llama3_8192_8b,53.4
 sg_llama3_70b_inst,51.959999999999994
+gemma-2-2b-it,52.08
 Qwen2_5_0_5B_Instruct,35.28
 cross_openhermes_llama3_70b_4096_inst,53.2
 cross_openhermes_llama3_8b_4096_2_inst,52.28

results/cultural_reasoning/zero_shot/us_eval.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.6448598130841121
 Meta-Llama-3-8B-Instruct,0.7009345794392523
 Meta-Llama-3.1-70B-Instruct,0.8411214953271028
 Qwen2_5_3B_Instruct,0.6728971962616822
+cross_openhermes_llama3_70b_4096_inst_2,0.8598130841121495
 SeaLLMs-v3-7B-Chat,0.6915887850467289
 Qwen2_5_72B_Instruct,0.8598130841121495
 gemma-2-9b-it,0.8130841121495327

results/dialogue/zero_shot/dialogsum.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.2519360474995096,0.3481981488260775,0.132
 Meta-Llama-3-8B-Instruct,0.23978455271183616,0.33971099717559883,0.1203340311564728,0.2593086298034369
 Meta-Llama-3.1-70B-Instruct,0.2526239717396146,0.35714386898604744,0.1258832921736473,0.27484475405914904
 Qwen2_5_3B_Instruct,0.22107390172674926,0.32206286484028823,0.10065030710901035,0.24050853323094928
+cross_openhermes_llama3_70b_4096_inst_2,0.2696117118557506,0.3743401999085179,0.14161035346358444,0.2928845821951494
 SeaLLMs-v3-7B-Chat,0.24891094210680076,0.35393482223136147,0.12172072639345373,0.27107727769558715
 Qwen2_5_72B_Instruct,0.23460549655507293,0.3373580017785426,0.10893746645433498,0.25752102143234123
 gemma-2-9b-it,0.2560682231168516,0.36247455000865003,0.12571639767749476,0.2800137216644101

results/dialogue/zero_shot/dream.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.8613424791768741
 Meta-Llama-3-8B-Instruct,0.8946594806467418
 Meta-Llama-3.1-70B-Instruct,0.9559039686428221
 Qwen2_5_3B_Instruct,0.9029887310142087
+cross_openhermes_llama3_70b_4096_inst_2,0.9549240568348849
 SeaLLMs-v3-7B-Chat,0.9265066144047036
 Qwen2_5_72B_Instruct,0.9627633512983832
 gemma-2-9b-it,0.9416952474277315

results/dialogue/zero_shot/samsum.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.2961783902880866,0.40739117705606903,0.16
 Meta-Llama-3-8B-Instruct,0.2846315092346869,0.39397110152251813,0.154320846916639,0.30560257926490364
 Meta-Llama-3.1-70B-Instruct,0.28934874612070227,0.4036295731242805,0.15211190810296196,0.31230475713486433
 Qwen2_5_3B_Instruct,0.26935624341081515,0.380865832002109,0.13872106416227833,0.28848183406805816
+cross_openhermes_llama3_70b_4096_inst_2,0.31836805920341904,0.432137300473344,0.18274124314511622,0.34022563399179695
 SeaLLMs-v3-7B-Chat,0.2959981719045788,0.4078820748825196,0.16338306782652476,0.316729373004692
 Qwen2_5_72B_Instruct,0.28852247889830335,0.3996215000271418,0.15494490129237035,0.31100103537539775
 gemma-2-9b-it,0.3100514077180449,0.4289412957792292,0.16727050182456474,0.3339424255503407

results/emotion/zero_shot/ind_emotion.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.6704545454545454
 Meta-Llama-3-8B-Instruct,0.6522727272727272
 Meta-Llama-3.1-70B-Instruct,0.7159090909090909
 Qwen2_5_3B_Instruct,0.5522727272727272
+cross_openhermes_llama3_70b_4096_inst_2,0.7068181818181818
 SeaLLMs-v3-7B-Chat,0.6454545454545455
 Qwen2_5_72B_Instruct,0.7068181818181818
 gemma-2-9b-it,0.7477272727272727

results/emotion/zero_shot/sst2.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.926605504587156
 Meta-Llama-3-8B-Instruct,0.8784403669724771
 Meta-Llama-3.1-70B-Instruct,0.9529816513761468
 Qwen2_5_3B_Instruct,0.8245412844036697
+cross_openhermes_llama3_70b_4096_inst_2,0.9415137614678899
 SeaLLMs-v3-7B-Chat,0.9403669724770642
 Qwen2_5_72B_Instruct,0.9334862385321101
 gemma-2-9b-it,0.9311926605504587

results/flores_translation/zero_shot/ind2eng.csv

@@ -7,6 +7,7 @@ cross_openhermes_llama3_8b_4096_inst,0.37782883404862155
 Meta-Llama-3-8B-Instruct,0.33079891679041123
 Meta-Llama-3.1-70B-Instruct,0.43366494500251235
 Qwen2_5_3B_Instruct,0.3316936422167389
+cross_openhermes_llama3_70b_4096_inst_2,0.41785038798707536
 SeaLLMs-v3-7B-Chat,0.3594829412574955
 gemma-2-9b-it,0.40786563079141763
 Meta-Llama-3-70B-Instruct,0.3830092775167675

results/flores_translation/zero_shot/vie2eng.csv

@@ -7,6 +7,7 @@ cross_openhermes_llama3_8b_4096_inst,0.28905588559612455
 Meta-Llama-3-8B-Instruct,0.2647448190950291
 Meta-Llama-3.1-70B-Instruct,0.37244508311079816
 Qwen2_5_3B_Instruct,0.27312609009801636
+cross_openhermes_llama3_70b_4096_inst_2,0.35523251361264646
 SeaLLMs-v3-7B-Chat,0.30981028289420137
 gemma-2-9b-it,0.3367700653885
 Meta-Llama-3-70B-Instruct,0.3230140263371192

results/flores_translation/zero_shot/zho2eng.csv

@@ -7,6 +7,7 @@ cross_openhermes_llama3_8b_4096_inst,0.2258901846942186
 Meta-Llama-3-8B-Instruct,0.199495011482748
 Meta-Llama-3.1-70B-Instruct,0.2832594176173152
 Qwen2_5_3B_Instruct,0.2245195134637718
+cross_openhermes_llama3_70b_4096_inst_2,0.272938440868618
 SeaLLMs-v3-7B-Chat,0.2516593644617717
 gemma-2-9b-it,0.267527968123433
 Meta-Llama-3-70B-Instruct,0.24397819518058994

results/flores_translation/zero_shot/zsm2eng.csv

@@ -7,6 +7,7 @@ cross_openhermes_llama3_8b_4096_inst,0.37996622288549425
 Meta-Llama-3-8B-Instruct,0.31625368345049
 Meta-Llama-3.1-70B-Instruct,0.4462132282683508
 Qwen2_5_3B_Instruct,0.31056841204320457
+cross_openhermes_llama3_70b_4096_inst_2,0.439568878723126
 SeaLLMs-v3-7B-Chat,0.3484133510670942
 gemma-2-9b-it,0.4234100394581857
 Meta-Llama-3-70B-Instruct,0.3957287030176054

results/fundamental_nlp_tasks/zero_shot/c3.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.7718773373223635
 Meta-Llama-3-8B-Instruct,0.8515332834704562
 Meta-Llama-3.1-70B-Instruct,0.9603590127150337
 Qwen2_5_3B_Instruct,0.8668661181750187
+cross_openhermes_llama3_70b_4096_inst_2,0.9420344053851907
 SeaLLMs-v3-7B-Chat,0.9143605086013463
 Qwen2_5_72B_Instruct,0.9596110695587136
 gemma-2-9b-it,0.9222139117427075

results/fundamental_nlp_tasks/zero_shot/cola.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.7660594439117929
 Meta-Llama-3-8B-Instruct,0.6548418024928092
 Meta-Llama-3.1-70B-Instruct,0.850431447746884
 Qwen2_5_3B_Instruct,0.6644295302013423
+cross_openhermes_llama3_70b_4096_inst_2,0.8609779482262704
 SeaLLMs-v3-7B-Chat,0.785234899328859
 Qwen2_5_72B_Instruct,0.8571428571428571
 gemma-2-9b-it,0.7938638542665388

results/fundamental_nlp_tasks/zero_shot/mnli.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.57
 Meta-Llama-3-8B-Instruct,0.546
 Meta-Llama-3.1-70B-Instruct,0.7015
 Qwen2_5_3B_Instruct,0.7465
+cross_openhermes_llama3_70b_4096_inst_2,0.7481549345956126
 SeaLLMs-v3-7B-Chat,0.653
 Qwen2_5_72B_Instruct,0.8445
 gemma-2-9b-it,0.716

results/fundamental_nlp_tasks/zero_shot/mrpc.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.7303921568627451
 Meta-Llama-3-8B-Instruct,0.678921568627451
 Meta-Llama-3.1-70B-Instruct,0.7696078431372549
 Qwen2_5_3B_Instruct,0.5661764705882353
+cross_openhermes_llama3_70b_4096_inst_2,0.7916666666666666
 SeaLLMs-v3-7B-Chat,0.7475490196078431
 Qwen2_5_72B_Instruct,0.8014705882352942
 gemma-2-9b-it,0.7401960784313726

results/fundamental_nlp_tasks/zero_shot/ocnli.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.5183050847457628
 Meta-Llama-3-8B-Instruct,0.44033898305084745
 Meta-Llama-3.1-70B-Instruct,0.6423728813559322
 Qwen2_5_3B_Instruct,0.6145762711864406
+cross_openhermes_llama3_70b_4096_inst_2,0.6759322033898305
 SeaLLMs-v3-7B-Chat,0.5698305084745763
 Qwen2_5_72B_Instruct,0.7684745762711864
 gemma-2-9b-it,0.6189830508474576

results/fundamental_nlp_tasks/zero_shot/qnli.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.7596558667398865
 Meta-Llama-3-8B-Instruct,0.6025993044114956
 Meta-Llama-3.1-70B-Instruct,0.9026176093721399
 Qwen2_5_3B_Instruct,0.7645982061138569
+cross_openhermes_llama3_70b_4096_inst_2,0.9086582463847702
 SeaLLMs-v3-7B-Chat,0.7159070107999268
 Qwen2_5_72B_Instruct,0.9082921471718836
 gemma-2-9b-it,0.9070107999267801

results/fundamental_nlp_tasks/zero_shot/rte.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.6967509025270758
 Meta-Llama-3-8B-Instruct,0.6173285198555957
 Meta-Llama-3.1-70B-Instruct,0.8483754512635379
 Qwen2_5_3B_Instruct,0.779783393501805
+cross_openhermes_llama3_70b_4096_inst_2,0.8916967509025271
 SeaLLMs-v3-7B-Chat,0.7870036101083032
 Qwen2_5_72B_Instruct,0.9025270758122743
 gemma-2-9b-it,0.7472924187725631

results/fundamental_nlp_tasks/zero_shot/wnli.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.4647887323943662
 Meta-Llama-3-8B-Instruct,0.4788732394366197
 Meta-Llama-3.1-70B-Instruct,0.8450704225352113
 Qwen2_5_3B_Instruct,0.647887323943662
+cross_openhermes_llama3_70b_4096_inst_2,0.8450704225352113
 SeaLLMs-v3-7B-Chat,0.5915492957746479
 Qwen2_5_72B_Instruct,0.8169014084507042
 gemma-2-9b-it,0.7746478873239436

results/general_reasoning/zero_shot/c_eval.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.44707347447073476
 Meta-Llama-3-8B-Instruct,0.4775840597758406
 Meta-Llama-3.1-70B-Instruct,0.6612702366127023
 Qwen2_5_3B_Instruct,0.6537982565379825
+cross_openhermes_llama3_70b_4096_inst_2,0.6133250311332503
 SeaLLMs-v3-7B-Chat,0.7658779576587795
 Qwen2_5_72B_Instruct,0.8325031133250311
 gemma-2-9b-it,0.5523038605230386

results/general_reasoning/zero_shot/cmmlu.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.4547573821447073
 Meta-Llama-3-8B-Instruct,0.4839405974788465
 Meta-Llama-3.1-70B-Instruct,0.6814885166637886
 Qwen2_5_3B_Instruct,0.6621481609393887
+cross_openhermes_llama3_70b_4096_inst_2,0.6392678293904335
 SeaLLMs-v3-7B-Chat,0.7684337765498187
 Qwen2_5_72B_Instruct,0.8343982041098256
 gemma-2-9b-it,0.5700224486271801

results/general_reasoning/zero_shot/indommlu.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.5097803591695039
 Meta-Llama-3-8B-Instruct,0.5264703918819681
 Meta-Llama-3.1-70B-Instruct,0.6740770411910008
 Qwen2_5_3B_Instruct,0.49656185326123237
+cross_openhermes_llama3_70b_4096_inst_2,0.6559182855998398
 SeaLLMs-v3-7B-Chat,0.5267374324053675
 Qwen2_5_72B_Instruct,0.6380933306629281
 gemma-2-9b-it,0.606983109686895

results/general_reasoning/zero_shot/mmlu.csv

@@ -8,12 +8,10 @@ Qwen2-72B-Instruct,0.7922774401144083
 cross_openhermes_llama3_8b_4096_inst,0.556381837683232
 Meta-Llama-3-8B-Instruct,0.6005720414730068
 Meta-Llama-3.1-70B-Instruct,0.8058634250983197
-sg_llama3_8192_8b_np,0.6528423310690025
 Qwen2_5_3B_Instruct,0.6118698605648909
-Meta-Llama-3-8B-Instruct_np,0.6619949946371112
+cross_openhermes_llama3_70b_4096_inst_2,0.7551662495530926
 SeaLLMs-v3-7B-Chat,0.6670003575259207
 Qwen2_5_72B_Instruct,0.8129424383267787
-cross_openhermes_llama3_8b_4096_inst_np,0.5601001072577761
 gemma-2-9b-it,0.7100464783696818
 Meta-Llama-3-70B-Instruct,0.7649624597783339
 Qwen2_5_14B_Instruct,0.7542366821594566
@@ -23,6 +21,5 @@ gemma-2-2b-it,0.5706828745084018
 llama3-8b-cpt-sea-lionv2-instruct,0.6130854486950303
 Qwen2_5_0_5B_Instruct,0.461136932427601
 GPT4o_0513,0.8308187343582409
-llama3-8b-cpt-sea-lionv2-instruct_np,0.6518412584912406
 cross_openhermes_llama3_70b_4096_inst,0.7400071505184126
 cross_openhermes_llama3_8b_4096_2_inst,0.5785484447622453

results/general_reasoning/zero_shot/zbench.csv

@@ -9,6 +9,7 @@ cross_openhermes_llama3_8b_4096_inst,0.3333333333333333
 Meta-Llama-3-8B-Instruct,0.3333333333333333
 Meta-Llama-3.1-70B-Instruct,0.48484848484848486
 Qwen2_5_3B_Instruct,0.5757575757575758
+cross_openhermes_llama3_70b_4096_inst_2,0.48484848484848486
 SeaLLMs-v3-7B-Chat,0.5454545454545454
 Qwen2_5_72B_Instruct,0.696969696969697
 gemma-2-9b-it,0.48484848484848486