Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multiple Choice Question Answering (Multiple) on Earth Observation
Loading...
87.56
IoU
GPT-4.1
84.2736
85.1268
85.98
86.8332
Mar 20, 2026
IoU
Accuracy
Rank
Updated 3d ago
Evaluation Results
Method
Method
Links
IoU
Accuracy
Rank
GPT-4.1
Size (B)=1800*
2026.03
87.56
78.19
2.83
Qwen3
Size (B)=235-A22
2026.03
87.4
80.97
2.17
EVE-Instruct
Size (B)=24
2026.03
86.12
77.73
3.5
Mistral Medium 3.1
Size (B)=200*
2026.03
85.44
76.33
4.17
MiniMax m2.5
Size (B)=230A10
2026.03
84.82
77.72
5.17
GPT OSS
Size (B)=120A5
2026.03
84.56
76.79
4.83
GPT-5 nano
Size (B)=20*
2026.03
84.4
76.1
5.33
Feedback
Search any
task
Search any
task