List your company

Physics Reasoning on QFT Synthetic Medium

88.8AccuracyGemini-2.5-flash
23.69640.59857.574.402Apr 21, 2026

Evaluation results

MethodLinks
Gemini-2.5-flashModel Type=Proprietary2026.0488.897.5
Claude-Opus-4.5Model Type=Proprietary2026.0485.293.8
OSS-20bModel Type=Open-Weight2026.047693.8
Qwen3-4B-Thinking-2507Model Type=Open-Weight2026.0449.568.8
Qwen3-4B-Instruct-2507Model Type=Open-Weight2026.0433.246.2
DeepSeek-R1-Distill-Qwen-7BModel Type=Open-Weight2026.0426.250