Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Physics Reasoning on Synthetic Numeric
Loading...
21.9
Accuracy
Qwen2.5-32B + RL (synthetic)
4.116
8.733
13.35
17.967
Apr 13, 2026
Accuracy
Updated 5d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2.5-32B + RL (synthetic)
Model=Qwen2.5-32B, Pos...
2026.04
21.9
Qwen3-30B + RL (synthetic)
Model=Qwen3-30B, Post-...
2026.04
17.4
Qwen2.5-14B + RL (synthetic)
Model=Qwen2.5-14B, Pos...
2026.04
17
Qwen2.5-7B + RL (synthetic)
Model=Qwen2.5-7B, Post...
2026.04
16.3
Qwen3-30B
Model=Qwen3-30B, Post-...
2026.04
14.8
Qwen2.5-3B + RL (synthetic)
Model=Qwen2.5-3B, Post...
2026.04
12.5
Qwen2.5-32B
Model=Qwen2.5-32B, Pos...
2026.04
8.9
Qwen2.5-7B
Model=Qwen2.5-7B, Post...
2026.04
7.7
Qwen2.5-14B
Model=Qwen2.5-14B, Pos...
2026.04
7
Qwen2.5-3B
Model=Qwen2.5-3B, Post...
2026.04
4.8
Feedback
Search any
task
Search any
task