Math Reasoning on AIME 24 (Pass@8)
86.7Pass@8 ScoreRFT
Evaluation Results
| Method | Links | |
|---|---|---|
| RFTBase Model=Qwen3-4B-Instruct2026.04 | 86.7 | |
| SRTBase Model=Qwen3-4B-Instruct2026.04 | 86.7 | |
| SD-ZEROBase Model=Qwen3-4B-Instruct2026.04 | 86.7 | |
| SFTBase Model=Qwen3-4B-Instruct2026.04 | 83.3 | |
| SFTBase Model=Olmo-3-7B-Instruct2026.04 | 83.3 | |
| SRTBase Model=Olmo-3-7B-Instruct2026.04 | 83.3 | |
| SD-ZEROBase Model=Olmo-3-7B-Instruct2026.04 | 83.3 | |
| GRPOBase Model=Qwen3-4B-Instruct2026.04 | 80 | |
| SDFTBase Model=Qwen3-4B-Instruct2026.04 | 80 | |
| Olmo-3-7B-InstructBase Model=Olmo-3-7B-Instruct2026.04 | 80 | |
| RFTBase Model=Olmo-3-7B-Instruct2026.04 | 80 | |
| GRPOBase Model=Olmo-3-7B-Instruct2026.04 | 80 | |
| SDFTBase Model=Olmo-3-7B-Instruct2026.04 | 80 | |
| Qwen3-4B-InstructBase Model=Qwen3-4B-Instruct2026.04 | 76.7 |