TRAIL / leaderboard_gaia.csv
jitinpatronus's picture
Update leaderboard_gaia.csv
2ca0676 verified
raw
history blame contribute delete
495 Bytes
Rank,Model,Joint Accuracy,Categorical F1,Location Accuracy,Date
1,Gemini-2.5-Pro-Preview-05-06,0.183,0.389,0.546,2025-05-14
2,Gemini-2.5-Flash-Preview-04-17,0.100,0.337,0.372,2025-05-14
3,Open AI o3,0.092,0.296,0.535,2025-05-14
4,Anthropic Claude-3.7-Sonnet,0.047,0.254,0.204,2025-05-14
5,GPT-4.1,0.028,0.218,0.107,2025-05-14
6,Open AI o1,0.013,0.138,0.040,2025-05-14
7,Llama-4-Maverick-17B-128E-Instruct,0.000,0.122,0.023,2025-05-14
8,Llama-4-Scout-17B-16E-Instruct,0.000,0.041,0.000,2025-05-14