List your company

Physics Reasoning on IPhO Mechanics

40AccuracyQwen3-30B + RL (synthetic)
4.307213.573622.8432.1064Apr 13, 2026

Evaluation results

MethodLinks
Qwen3-30B + RL (synthetic)Model=Qwen3-30B, Post-training Stage=RL (synthetic)2026.0440
Qwen3-30BModel=Qwen3-30B, Post-training Stage=Instruct2026.0435.6
Qwen2.5-32B + RL (synthetic)Model=Qwen2.5-32B, Post-training Stage=RL (synthetic)2026.0425.2
Qwen2.5-14B + RL (synthetic)Model=Qwen2.5-14B, Post-training Stage=RL (synthetic)2026.0420.45
Qwen2.5-32BModel=Qwen2.5-32B, Post-training Stage=Instruct2026.0419.8
Qwen2.5-14BModel=Qwen2.5-14B, Post-training Stage=Instruct2026.0416.07
Qwen2.5-7B + RL (synthetic)Model=Qwen2.5-7B, Post-training Stage=RL (synthetic)2026.0415.1
Qwen2.5-3B + RL (synthetic)Model=Qwen2.5-3B, Post-training Stage=RL (synthetic)2026.0413.15
Qwen2.5-7BModel=Qwen2.5-7B, Post-training Stage=Instruct2026.0410.7
Qwen2.5-3BModel=Qwen2.5-3B, Post-training Stage=Instruct2026.045.68