Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multiple Choice Question Answering (Single) on Earth Observation
Loading...
96.35
Accuracy
EVE-Instruct
89.5068
91.2834
93.06
94.8366
Mar 20, 2026
Accuracy
Rank
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
Rank
EVE-Instruct
Size (B)=24
2026.03
96.35
3.5
Qwen3
Size (B)=235-A22
2026.03
95.16
2.17
Mistral Medium 3.1
Size (B)=200*
2026.03
95
4.17
MiniMax m2.5
Size (B)=230A10
2026.03
94.95
5.17
GPT-4.1
Size (B)=1800*
2026.03
94.37
2.83
GPT-5 nano
Size (B)=20*
2026.03
91.99
5.33
GPT OSS
Size (B)=120A5
2026.03
89.77
4.83
Feedback
Search any
task
Search any
task