model,accuracy
gpt-3-5-turbo-1106,71.7196414
gpt35turbo,71.96414018
gpt4omini,83.21108394
gpt4o,88.83455583
gpt-4o-2024-08-06,89.73105134
gpt-4-0125-preview,88.50855746
gpt-4-1106-preview,88.59005705
haiku,61.69519152
sonnet3,60.06519967
opus,81.01059495
sonnet35,79.95110024
mistralnemo,71.47514262
mistralsmall,68.4596577
mistral-large-2402,56.72371638
mistrallarge,85.8190709
llama3-8b,70.25264874
llama3-70b,83.04808476
llama3-1-8b,71.23064385
llama3-1-70b,84.10757946
llama3-1-405b,85.65607172
gemma2-9b,76.20211899
gemma2-27b,79.21760391
mistral-7b-v1,58.10920945
mistral-7b-v2,54.44172779
mixtral-8x22B,74.00162999
qwen1-5-72b-chat,80.11409943
qwen2-72b,83.21108394