List your company

Question Generation on Physics Word Problem Dataset

58.73Conformity ScoreLlama-3.2-3B-Instruct
0.656415.733230.8145.8868Jun 14, 2026

Evaluation results

MethodLinks
Llama-3.2-3B-Instruct2026.0658.73
Mistral-7B-Instruct-v0.22026.0631.88
DeepSeek-R12026.067.61
ARVRE2026.065.91
GPT-3.5-Turbo2026.062.89