List your company

Question Answering on OpenbookQA ar

53.54AccuracyGamayun
18.866427.868236.8745.8718Dec 25, 2025

Evaluation results

MethodLinks
Gamayunscenario=zero-shot2025.1253.54
Qwen2.5scenario=zero-shot2025.1248.48
Qwen3scenario=zero-shot, thinking_mode=no-thinking2025.1244.44
Gemma3scenario=zero-shot2025.1237.58
Llama3.2scenario=zero-shot2025.1237.17
EuroLMscenario=zero-shot2025.1220.2