List your company

Open-Ended Question Answering on EO and Earth Sciences Open-Ended QA

96.4Judge ScoreEVE-Instruct
87.008889.446991.88594.3231Mar 20, 2026

Evaluation results

MethodLinks
EVE-InstructSize (B)=24, Evaluation Protocol=0-shot2026.0396.4—
Qwen3Size (B)=30-A3, Evaluation Protocol=0-shot2026.0394.9250.7
Gemma3Size (B)=27, Evaluation Protocol=0-shot2026.0394.4150.92
Mistral Small 3.2Size (B)=24, Evaluation Protocol=0-shot2026.0391.7851.69
Llama4 ScoutSize (B)=109-A17, Evaluation Protocol=0-shot2026.0387.3753.95