Mathematical Reasoning on AIME 23
8.05Pass@1ICT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ICTModel Size=Qwen2.5-7B2026.06 | 8.05 | 16.95 | |
| STAPOModel Size=Qwen2.5-7B2026.06 | 7.2 | 13.56 | |
| 20-EntropyModel Size=Qwen2.5-7B2026.06 | 6.78 | 13.56 | |
| GRPOModel Size=Qwen2.5-7B2026.06 | 5.51 | 6.78 | |
| ICTModel Size=Qwen2.5-1.5B2026.06 | 5.02 | 13.41 | |
| BaseModel Size=Qwen2.5-7B2026.06 | 4.66 | 8.47 | |
| STAPOModel Size=Qwen2.5-1.5B2026.06 | 4.45 | 11.21 | |
| 20-EntropyModel Size=Qwen2.5-1.5B2026.06 | 4.31 | 10.34 | |
| GRPOModel Size=Qwen2.5-1.5B2026.06 | 4.11 | 10.21 | |
| BaseModel Size=Qwen2.5-1.5B2026.06 | 3.45 | 6.9 | |
| BaseModel Size=Qwen2.5-0.5B2026.06 | 0.86 | 3.45 | |
| GRPOModel Size=Qwen2.5-0.5B2026.06 | 0.86 | 3.45 | |
| 20-EntropyModel Size=Qwen2.5-0.5B2026.06 | 0.86 | 3.45 | |
| ICTModel Size=Qwen2.5-0.5B2026.06 | 0.86 | 3.45 | |
| STAPOModel Size=Qwen2.5-0.5B2026.06 | 0 | 0 |