List your company

Physics Reasoning on QFT Synthetic Easy

89AccuracyGemini-2.5-flash
38.24851.42464.677.776Apr 21, 2026

Evaluation results

MethodLinks
Gemini-2.5-flashModel Type=Proprietary2026.048996.2
Claude-Opus-4.5Model Type=Proprietary2026.0481.595
OSS-20bModel Type=Open-Weight2026.0481.595
Qwen3-4B-Thinking-2507Model Type=Open-Weight2026.0469.583.8
Qwen3-4B-Instruct-2507Model Type=Open-Weight2026.0453.575
DeepSeek-R1-Distill-Qwen-7BModel Type=Open-Weight2026.0440.267.5