Spaces:
Running
Running
model,accuracy | |
gpt-3-5-turbo-1106,26.97636512 | |
gpt35turbo,32.76283619 | |
gpt4omini,48.32925835 | |
gpt4o,61.45069275 | |
gpt-4o-2024-08-06,62.02118989 | |
gpt-4-0125-preview,61.61369193 | |
gpt-4-1106-preview,59.8207009 | |
haiku,25.34637327 | |
sonnet3,34.47432763 | |
opus,52.89323553 | |
sonnet35,51.50774246 | |
mistralnemo,37.73431133 | |
mistralsmall,43.27628362 | |
mistral-large-2402,48.65525672 | |
mistrallarge,43.92828036 | |
gemini-1-5-flash,45.31377343 | |
llama3-8b,21.43439283 | |
llama3-70b,30.399348 | |
llama3-1-8b,37.97881011 | |
llama3-1-70b,54.19722901 | |
llama3-1-405b,52.56723716 | |
gemma2-9b,38.95680522 | |
gemma2-27b,43.03178484 | |
mistral-7b-v1,19.5599022 | |
mistral-7b-v2,34.800326 | |
mixtral-8x22B,44.25427873 | |
qwen1-5-72b-chat,44.74327628 | |
qwen2-72b,48.65525672 |