List your company

Physics Reasoning on HCV

59AccuracyQwen3-30B + RL (synthetic)
30.81638.13345.4552.767Apr 13, 2026

Evaluation results

MethodLinks
Qwen3-30B + RL (synthetic)Model=Qwen3-30B, Post-training Stage=RL (synthetic)2026.0459
Qwen3-30BModel=Qwen3-30B, Post-training Stage=Instruct2026.0453.9
Qwen2.5-32B + RL (synthetic)Model=Qwen2.5-32B, Post-training Stage=RL (synthetic)2026.0453.9
Qwen2.5-14B + RL (synthetic)Model=Qwen2.5-14B, Post-training Stage=RL (synthetic)2026.0451.7
Qwen2.5-32BModel=Qwen2.5-32B, Post-training Stage=Instruct2026.0450.6
Qwen2.5-14BModel=Qwen2.5-14B, Post-training Stage=Instruct2026.0449.3
Qwen2.5-7B + RL (synthetic)Model=Qwen2.5-7B, Post-training Stage=RL (synthetic)2026.0446.3
Qwen2.5-7BModel=Qwen2.5-7B, Post-training Stage=Instruct2026.0444.5
Qwen2.5-3B + RL (synthetic)Model=Qwen2.5-3B, Post-training Stage=RL (synthetic)2026.0439.5
Qwen2.5-3BModel=Qwen2.5-3B, Post-training Stage=Instruct2026.0431.9