List your company

Multiple Choice Question Answering (Single) on Earth Observation

96.35AccuracyEVE-Instruct
89.506891.283493.0694.8366Mar 20, 2026

Evaluation results

MethodLinks
EVE-InstructSize (B)=242026.0396.353.5
Qwen3Size (B)=235-A222026.0395.162.17
Mistral Medium 3.1Size (B)=200*2026.03954.17
MiniMax m2.5Size (B)=230A102026.0394.955.17
GPT-4.1Size (B)=1800*2026.0394.372.83
GPT-5 nanoSize (B)=20*2026.0391.995.33
GPT OSSSize (B)=120A52026.0389.774.83