LLMCalc / src /results_1.6.csv
carbonnnnn's picture
first sample
b7fabea
raw
history blame
12.1 kB
,"-, clemscore","all, Average % Played","all, Average Quality Score","imagegame, % Played","imagegame, Quality Score","imagegame, Quality Score (std)","privateshared, % Played","privateshared, Quality Score","privateshared, Quality Score (std)","referencegame, % Played","referencegame, Quality Score","referencegame, Quality Score (std)","taboo, % Played","taboo, Quality Score","taboo, Quality Score (std)","wordle, % Played","wordle, Quality Score","wordle, Quality Score (std)","wordle_withclue, % Played","wordle_withclue, Quality Score","wordle_withclue, Quality Score (std)","wordle_withcritic, % Played","wordle_withcritic, Quality Score","wordle_withcritic, Quality Score (std)"
CodeLlama-34b-Instruct-hf-t0.0--CodeLlama-34b-Instruct-hf-t0.0,14.35,33.57,42.76,0.0,,,0.0,,,100.0,94.44,22.97,51.67,51.61,50.8,56.67,0.0,0.0,26.67,25.0,46.29,0.0,,
Meta-Llama-3-70B-Instruct-hf-t0.0--Meta-Llama-3-70B-Instruct-hf-t0.0,35.11,80.72,43.5,0.0,,,100.0,84.37,13.69,100.0,64.44,48.0,91.67,70.3,39.37,90.0,1.85,6.81,96.67,14.37,32.34,86.67,25.64,39.08
Meta-Llama-3-8B-Instruct-hf-t0.0--Meta-Llama-3-8B-Instruct-hf-t0.0,19.99,76.1,26.27,0.0,,,96.0,58.91,30.05,100.0,46.11,49.99,100.0,37.78,45.08,86.67,0.0,0.0,83.33,14.0,33.91,66.67,0.83,3.73
Meta-Llama-3.1-405B-Instruct-Turbo-t0.0--Meta-Llama-3.1-405B-Instruct-Turbo-t0.0,52.11,90.12,57.82,62.5,94.12,12.55,100.0,84.24,29.65,100.0,80.0,40.11,95.0,76.61,36.03,93.33,7.14,12.72,93.33,29.7,34.87,86.67,32.95,35.63
Meta-Llama-3.1-70B-Instruct-t0.0--Meta-Llama-3.1-70B-Instruct-t0.0,38.83,82.14,47.27,0.0,,,100.0,85.69,13.94,100.0,72.78,44.63,88.33,75.16,34.69,93.33,1.43,5.25,93.33,19.29,33.55,100.0,29.28,36.5
Meta-Llama-3.1-8B-Instruct-t0.0--Meta-Llama-3.1-8B-Instruct-t0.0,18.36,72.91,25.18,0.0,,,82.0,29.31,25.61,100.0,47.78,50.09,88.33,50.0,47.7,96.67,0.0,0.0,76.67,12.32,29.82,66.67,11.67,31.11
Mistral-7B-Instruct-v0.1-t0.0--Mistral-7B-Instruct-v0.1-t0.0,8.01,37.14,21.58,0.0,,,20.0,1.21,2.58,100.0,55.0,49.89,100.0,31.67,45.07,0.0,,,23.33,0.0,0.0,16.67,20.0,44.72
Mistral-7B-Instruct-v0.2-t0.0--Mistral-7B-Instruct-v0.2-t0.0,9.75,36.91,26.42,0.0,,,0.0,,,100.0,38.33,48.76,65.0,0.0,0.0,50.0,0.0,0.0,26.67,43.75,49.55,16.67,50.0,50.0
Mistral-Large-Instruct-2407-t0.0--Mistral-Large-Instruct-2407-t0.0,45.39,82.21,55.21,7.5,100.0,0.0,78.0,81.39,13.12,100.0,81.11,39.25,96.67,71.84,36.57,100.0,0.67,3.65,93.33,21.73,32.97,100.0,29.72,41.79
Mixtral-8x22B-Instruct-v0.1-t0.0--Mixtral-8x22B-Instruct-v0.1-t0.0,12.69,52.14,24.33,0.0,,,0.0,,,100.0,36.67,48.32,58.33,40.0,49.71,96.67,0.0,0.0,60.0,15.0,33.3,50.0,30.0,41.4
Mixtral-8x7B-Instruct-v0.1-t0.0--Mixtral-8x7B-Instruct-v0.1-t0.0,8.17,47.62,17.15,0.0,,,0.0,,,61.67,41.44,49.49,51.67,9.68,30.05,96.67,0.0,0.0,76.67,19.13,35.28,46.67,15.48,36.08
Nous-Hermes-2-Mixtral-8x7B-SFT-t0.0--Nous-Hermes-2-Mixtral-8x7B-SFT-t0.0,11.95,39.68,30.12,0.0,,,0.0,,,97.78,36.93,48.4,93.33,47.92,47.36,0.0,,,53.33,15.62,30.1,33.33,20.0,42.16
Phi-3-mini-128k-instruct-t0.0--Phi-3-mini-128k-instruct-t0.0,6.33,34.52,18.34,0.0,,,0.0,,,100.0,36.67,48.32,98.33,0.0,0.0,0.0,,,33.33,20.0,42.16,10.0,16.67,28.87
Qwen1.5-0.5B-Chat-t0.0--Qwen1.5-0.5B-Chat-t0.0,0.12,25.72,0.48,0.0,,,0.0,,,0.0,,,86.67,1.92,13.87,46.67,0.0,0.0,40.0,0.0,0.0,6.67,0.0,0.0
Qwen1.5-1.8B-Chat-t0.0--Qwen1.5-1.8B-Chat-t0.0,0.0,15.24,0.0,0.0,,,0.0,,,0.0,,,93.33,0.0,0.0,0.0,,,10.0,0.0,0.0,3.33,0.0,
Qwen1.5-14B-Chat-t0.0--Qwen1.5-14B-Chat-t0.0,16.8,40.95,41.02,30.0,20.58,14.69,0.0,,,100.0,44.44,49.83,46.67,41.07,47.25,90.0,0.0,0.0,16.67,40.0,54.77,3.33,100.0,
Qwen1.5-32B-Chat-t0.0--Qwen1.5-32B-Chat-t0.0,15.41,63.69,24.19,67.5,42.15,29.29,20.0,35.52,9.63,100.0,12.78,33.48,61.67,42.79,47.39,93.33,0.0,0.0,60.0,16.85,33.34,43.33,19.23,38.4
Qwen1.5-72B-Chat-t0.0--Qwen1.5-72B-Chat-t0.0,30.37,80.05,37.94,65.0,50.0,25.53,92.0,52.87,20.39,100.0,37.22,48.47,73.33,73.11,43.02,96.67,0.69,3.71,90.0,20.93,39.03,43.33,30.77,48.04
Qwen1.5-7B-Chat-t0.0--Qwen1.5-7B-Chat-t0.0,2.58,30.24,8.53,0.0,,,0.0,,,100.0,20.56,40.52,98.33,13.56,33.26,0.0,,,10.0,0.0,0.0,3.33,0.0,
Qwen2-72B-Instruct-t0.0--Qwen2-72B-Instruct-t0.0,30.03,74.52,40.3,0.0,,,80.0,65.69,22.85,100.0,67.22,47.07,91.67,70.61,40.31,100.0,2.67,10.48,86.67,12.82,29.56,63.33,22.81,33.31
Qwen2-7B-Instruct-t0.0--Qwen2-7B-Instruct-t0.0,6.18,35.32,17.51,5.0,23.0,1.41,0.0,,,98.89,41.01,49.32,86.67,41.03,46.14,26.67,0.0,0.0,26.67,0.0,0.0,3.33,0.0,
SUS-Chat-34B-t0.0--SUS-Chat-34B-t0.0,14.11,54.4,25.93,2.5,29.0,,20.0,0.0,0.0,100.0,70.0,45.95,98.33,52.26,45.64,93.33,0.0,0.0,43.33,23.08,43.85,23.33,7.14,18.9
Starling-LM-7B-beta-t0.0--Starling-LM-7B-beta-t0.0,6.56,30.89,21.25,0.0,,,4.0,97.12,4.08,62.22,30.36,46.19,46.67,0.0,0.0,66.67,0.0,0.0,33.33,0.0,0.0,3.33,0.0,
WizardLM-13b-v1.2-t0.0--WizardLM-13b-v1.2-t0.0,11.48,39.57,29.0,0.0,,,42.0,10.11,21.96,100.0,71.11,45.45,35.0,64.29,45.12,26.67,0.0,0.0,53.33,6.25,25.0,20.0,22.22,40.37
WizardLM-70b-v1.0-t0.0--WizardLM-70b-v1.0-t0.0,17.4,46.19,37.66,0.0,,,0.0,,,100.0,81.67,38.8,56.67,70.59,44.58,73.33,0.0,0.0,56.67,17.84,34.09,36.67,18.18,40.45
Yi-1.5-34B-Chat-t0.0--Yi-1.5-34B-Chat-t0.0,7.67,52.38,14.65,0.0,,,0.0,,,100.0,43.33,49.69,66.67,0.0,0.0,96.67,0.0,0.0,70.0,18.25,36.48,33.33,11.67,31.48
Yi-1.5-6B-Chat-t0.0--Yi-1.5-6B-Chat-t0.0,6.73,41.43,16.25,0.0,,,0.0,,,88.33,34.59,47.72,65.0,0.0,0.0,86.67,0.0,0.0,33.33,20.0,42.16,16.67,26.67,43.46
Yi-1.5-9B-Chat-t0.0--Yi-1.5-9B-Chat-t0.0,4.37,38.1,11.48,0.0,,,0.0,,,51.67,41.94,49.61,41.67,0.0,0.0,86.67,0.0,0.0,46.67,7.14,26.73,40.0,8.33,28.87
Yi-34B-Chat-t0.0--Yi-34B-Chat-t0.0,8.27,40.86,20.25,35.0,9.07,10.84,26.0,8.02,17.17,3.33,33.33,51.64,68.33,41.46,49.88,83.33,0.0,0.0,43.33,26.92,43.85,26.67,22.92,36.66
aya-23-35B-t0.0--aya-23-35B-t0.0,13.35,47.9,27.88,0.0,,,82.0,31.48,15.69,100.0,42.78,49.61,90.0,40.43,45.63,0.0,,,33.33,19.17,31.93,30.0,5.56,16.67
aya-23-8B-t0.0--aya-23-8B-t0.0,11.72,45.24,25.9,0.0,,,50.0,35.71,33.91,100.0,35.0,47.83,100.0,22.22,40.44,40.0,0.0,0.0,13.33,50.0,57.74,13.33,12.5,25.0
claude-2.1-t0.0--claude-2.1-t0.0,32.5,82.14,39.57,0.0,,,100.0,74.92,26.26,100.0,50.56,50.14,95.0,64.91,45.93,96.67,7.59,21.16,86.67,21.6,39.58,96.67,17.82,35.34
claude-3-5-sonnet-20240620-t0.0--claude-3-5-sonnet-20240620-t0.0,57.08,89.64,63.68,97.5,97.1,10.08,100.0,89.57,10.67,100.0,91.11,28.54,33.33,72.5,28.75,100.0,15.0,23.45,100.0,41.44,34.92,96.67,39.02,34.81
claude-3-haiku-20240307-t0.0--claude-3-haiku-20240307-t0.0,22.49,79.52,28.28,0.0,,,100.0,50.46,34.83,100.0,17.22,37.86,63.33,78.95,32.11,100.0,0.0,0.0,100.0,8.44,21.27,93.33,14.58,31.64
claude-3-opus-20240229-t0.0--claude-3-opus-20240229-t0.0,42.42,83.1,51.05,0.0,,,100.0,95.32,6.4,100.0,29.44,45.71,88.33,83.65,32.11,100.0,20.0,28.65,96.67,46.09,38.59,96.67,31.78,35.15
claude-3-sonnet-20240229-t0.0--claude-3-sonnet-20240229-t0.0,30.53,85.24,35.82,0.0,,,100.0,60.81,25.28,100.0,27.22,44.63,100.0,73.61,36.73,100.0,10.67,23.33,100.0,20.5,33.65,96.67,22.13,33.35
codegemma-7b-it-t0.0--codegemma-7b-it-t0.0,15.3,51.95,29.45,0.0,,,42.0,0.0,0.0,81.67,96.6,18.19,83.33,26.0,44.31,96.67,0.0,0.0,43.33,14.1,30.31,16.67,40.0,54.77
command-r-plus-t0.0--command-r-plus-t0.0,24.94,74.9,33.3,0.0,,,,,,99.44,47.49,50.08,63.33,67.11,45.44,100.0,7.33,19.82,93.33,26.79,37.91,93.33,17.8,32.58
command-r-t0.0--command-r-t0.0,14.15,61.67,22.95,0.0,,,,,,100.0,23.33,42.41,63.33,44.74,47.63,93.33,0.0,0.0,66.67,30.0,44.13,46.67,16.67,36.4
dolphin-2.5-mixtral-8x7b-t0.0--dolphin-2.5-mixtral-8x7b-t0.0,15.1,46.38,32.55,0.0,,,48.0,58.95,25.96,100.0,35.0,47.83,100.0,41.11,46.79,0.0,,,43.33,7.69,27.74,33.33,20.0,42.16
gemini-1.0-pro-t0.0--gemini-1.0-pro-t0.0,26.95,80.14,33.63,30.0,49.08,26.5,76.0,63.7,19.97,100.0,46.11,49.99,85.0,55.23,44.53,90.0,0.74,3.85,86.67,12.82,32.76,93.33,7.74,21.98
gemini-1.5-flash-latest-t0.0--gemini-1.5-flash-latest-t0.0,32.0,76.14,42.03,0.0,,,98.0,78.18,20.17,100.0,61.11,48.89,91.67,57.88,43.61,96.67,0.69,3.71,66.67,33.33,38.9,80.0,20.97,31.07
gemini-1.5-pro-latest-t0.0--gemini-1.5-pro-latest-t0.0,41.9,81.29,51.55,0.0,,,94.0,88.7,10.41,100.0,65.0,47.83,85.0,70.59,35.84,100.0,10.67,22.43,93.33,41.37,39.25,96.67,32.99,35.32
gemma-1.1-2b-it-t0.0--gemma-1.1-2b-it-t0.0,2.91,22.62,12.87,0.0,,,0.0,,,100.0,20.0,40.11,45.0,14.81,36.2,0.0,,,6.67,0.0,0.0,6.67,16.66,23.57
gemma-1.1-7b-it-t0.0--gemma-1.1-7b-it-t0.0,14.14,49.67,28.46,0.0,,,6.0,10.83,10.1,100.0,92.22,26.86,35.0,52.38,51.18,73.33,0.0,0.0,76.67,6.52,22.88,56.67,8.82,26.43
gemma-2-27b-it-t0.0--gemma-2-27b-it-t0.0,3.51,11.9,29.51,0.0,,,0.0,,,75.0,38.52,48.85,5.0,0.0,0.0,0.0,,,0.0,,,3.33,50.0,
gemma-2-2b-it-t0.0--gemma-2-2b-it-t0.0,2.67,38.33,6.96,0.0,,,0.0,,,0.0,,,98.33,0.0,0.0,100.0,0.0,0.0,46.67,10.71,28.95,23.33,17.14,37.29
gemma-2-9b-it-t0.0--gemma-2-9b-it-t0.0,27.34,75.48,36.22,0.0,,,70.0,53.52,40.57,100.0,42.22,49.53,78.33,77.66,38.27,100.0,1.67,9.13,93.33,17.26,33.48,86.67,25.0,43.01
gemma-7b-it-t0.0--gemma-7b-it-t0.0,1.82,17.78,10.23,0.0,,,0.0,,,97.78,40.91,49.31,0.0,,,3.33,0.0,,3.33,0.0,,20.0,0.0,0.0
gpt-3.5-turbo-0125-t0.0--gpt-3.5-turbo-0125-t0.0,27.22,89.67,30.36,70.0,64.18,29.33,96.0,36.7,31.04,100.0,3.33,18.0,68.33,73.17,41.98,100.0,0.0,0.0,96.67,24.25,40.95,96.67,10.92,27.56
gpt-4-0125-preview-t0.0--gpt-4-0125-preview-t0.0,52.5,94.92,55.31,100.0,99.6,1.53,100.0,90.22,6.92,99.44,31.84,46.72,75.0,93.33,20.23,100.0,20.67,27.66,100.0,33.17,42.87,90.0,18.33,32.69
gpt-4-0613-t0.0--gpt-4-0613-t0.0,51.09,94.88,53.85,77.5,98.19,10.06,100.0,97.33,4.12,100.0,35.56,48.0,86.67,79.81,33.22,100.0,9.0,25.78,100.0,36.78,40.4,100.0,20.28,29.17
gpt-4-1106-preview-t0.0--gpt-4-1106-preview-t0.0,51.99,98.1,53.0,95.0,94.34,10.24,100.0,87.08,10.69,100.0,29.44,45.71,91.67,83.94,29.57,100.0,13.0,27.56,100.0,29.0,39.53,100.0,34.22,39.55
gpt-4-turbo-2024-04-09-t0.0--gpt-4-turbo-2024-04-09-t0.0,58.3,94.88,61.45,82.5,99.79,1.22,100.0,92.68,9.45,100.0,88.89,31.51,85.0,82.35,30.81,100.0,16.33,31.35,100.0,29.89,39.18,96.67,20.23,28.21
gpt-4o-2024-05-13-t0.0--gpt-4o-2024-05-13-t0.0,48.34,85.71,56.4,0.0,,,100.0,94.66,5.56,100.0,90.0,30.08,100.0,75.28,35.19,100.0,19.33,28.52,100.0,28.0,36.38,100.0,31.11,33.14
gpt-4o-2024-08-06-t0.0--gpt-4o-2024-08-06-t0.0,47.71,85.71,55.66,0.0,,,100.0,90.36,8.32,100.0,87.78,32.85,100.0,85.28,25.51,100.0,23.0,30.53,100.0,23.94,34.28,100.0,23.61,30.72
gpt-4o-mini-2024-07-18-t0.0--gpt-4o-mini-2024-07-18-t0.0,34.64,85.06,40.73,0.0,,,96.0,59.27,19.82,99.44,73.74,44.13,100.0,69.72,40.18,100.0,10.33,23.56,100.0,15.67,31.78,100.0,15.67,31.17
llama-2-70b-chat-hf-t0.0--llama-2-70b-chat-hf-t0.0,0.81,7.14,11.31,0.0,,,0.0,,,46.67,22.62,42.09,0.0,,,0.0,,,3.33,0.0,,0.0,,
mistral-large-2402-t0.0--mistral-large-2402-t0.0,28.17,66.86,42.14,0.0,,,98.0,77.07,27.28,100.0,25.0,43.42,60.0,88.89,31.87,63.33,5.26,22.94,83.33,26.8,36.21,63.33,29.82,40.57
mistral-medium-2312-t0.0--mistral-medium-2312-t0.0,16.43,49.25,33.36,0.0,,,22.0,15.28,24.12,76.11,48.91,50.17,30.0,88.89,32.34,80.0,0.0,0.0,83.33,26.8,42.67,53.33,20.31,40.02
openchat-3.5-0106-t0.0--openchat-3.5-0106-t0.0,17.1,52.57,32.52,35.0,0.86,3.21,98.0,56.86,23.59,100.0,93.33,25.01,65.0,64.1,48.6,10.0,0.0,0.0,40.0,12.5,31.08,20.0,0.0,0.0
openchat-3.5-1210-t0.0--openchat-3.5-1210-t0.0,18.22,51.19,35.6,15.0,3.17,7.76,80.0,60.82,24.23,100.0,90.56,29.33,40.0,66.67,48.15,46.67,0.0,0.0,53.33,20.83,40.14,23.33,7.14,18.9
openchat_3.5-t0.0--openchat_3.5-t0.0,23.64,63.52,37.22,50.0,8.7,11.65,38.0,73.36,22.12,100.0,73.89,44.05,100.0,45.0,49.32,90.0,0.0,0.0,36.67,15.15,31.14,30.0,44.44,52.7
sheep-duck-llama-2-13b-t0.0--sheep-duck-llama-2-13b-t0.0,5.39,31.9,16.9,0.0,,,0.0,,,96.67,1.72,13.05,83.33,4.0,19.79,0.0,,,23.33,28.57,48.8,20.0,33.33,51.64
sheep-duck-llama-2-70b-v1.1-t0.0--sheep-duck-llama-2-70b-v1.1-t0.0,21.5,41.19,52.2,0.0,,,0.0,,,100.0,83.33,37.37,55.0,90.91,29.19,60.0,0.0,0.0,43.33,42.31,44.94,30.0,44.44,46.4
tulu-2-dpo-70b-t0.0--tulu-2-dpo-70b-t0.0,12.62,49.76,25.37,0.0,,,0.0,,,100.0,16.67,37.37,68.33,68.29,47.11,80.0,0.0,0.0,53.33,16.88,29.83,46.67,25.0,42.74
vicuna-13b-v1.5-t0.0--vicuna-13b-v1.5-t0.0,7.01,39.52,17.73,0.0,,,20.0,20.27,8.84,100.0,0.0,0.0,46.67,60.71,49.73,53.33,0.0,0.0,36.67,21.21,40.2,20.0,4.17,10.21
vicuna-33b-v1.3-t0.0--vicuna-33b-v1.3-t0.0,11.27,23.81,47.32,0.0,,,0.0,,,100.0,0.0,0.0,46.67,89.29,31.5,0.0,,,10.0,16.67,28.87,10.0,83.33,28.87