Mathematical Reasoning on AMC (Mean Accuracy)
59.5Mean AccuracyDiSCTT
Evaluation Results
| Method | Links | |
|---|---|---|
| DiSCTTModel=Qwen-2.5-7B-Instruct2026.03 | 59.5 | |
| DiSCTTModel=Qwen-3-4B-Base2026.03 | 57 | |
| EVOL-RLModel=Qwen-2.5-7B-Instruct2026.03 | 55 | |
| EVOL-RLModel=Qwen-3-4B-Base2026.03 | 51.8 | |
| TTRLModel=Qwen-2.5-7B-Instruct2026.03 | 51.1 | |
| DiSCTTModel=Qwen-3-1.7B-Base2026.03 | 48.8 | |
| TTRLModel=Qwen-3-4B-Base2026.03 | 46.6 | |
| EVOL-RLModel=Qwen-3-1.7B-Base2026.03 | 44.9 | |
| TTRLModel=Qwen-3-1.7B-Base2026.03 | 40.2 | |
| BaseModel=Qwen-2.5-7B-Instruct2026.03 | 39.6 | |
| DiSCTTModel=LLaMA-3.2-3B-Instruct2026.03 | 39.1 | |
| BaseModel=Qwen-3-4B-Base2026.03 | 38.6 | |
| EVOL-RLModel=LLaMA-3.2-3B-Instruct2026.03 | 32.2 | |
| DiSCTTModel=Qwen-2.5-0.5B-Instruct2026.03 | 27.7 | |
| TTRLModel=LLaMA-3.2-3B-Instruct2026.03 | 27.2 | |
| DiSCTTModel=LLaMA-3.2-1B-Instruct2026.03 | 26.4 | |
| EVOL-RLModel=LLaMA-3.2-1B-Instruct2026.03 | 25.4 | |
| EVOL-RLModel=Qwen-2.5-0.5B-Instruct2026.03 | 23.1 | |
| TTRLModel=LLaMA-3.2-1B-Instruct2026.03 | 22.5 | |
| TTRLModel=Qwen-2.5-0.5B-Instruct2026.03 | 20.3 | |
| BaseModel=Qwen-3-1.7B-Base2026.03 | 19.8 | |
| BaseModel=LLaMA-3.2-1B-Instruct2026.03 | 15.4 | |
| BaseModel=LLaMA-3.2-3B-Instruct2026.03 | 12.5 | |
| BaseModel=Qwen-2.5-0.5B-Instruct2026.03 | 12.2 |