Math on SVAMP (Accuracy and Significance Testing)
94.2Accuracy (%)Ref. SOTA
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Ref. SOTAModel Type=Proprietary2026.03 | 94.2 | — | — | |
| EcoThink2026.03 | 92.8 | -1.4 | 0.068 | |
| DARTBase Model=Qwen3-0.6B2026.05 | 81.37 | — | — | |
| Original-SFTBase Model=Qwen3-0.6B2026.05 | 80.9 | — | — | |
| GRPOBase Model=Qwen3-0.6B2026.05 | 80 | — | — | |
| STaRBase Model=Qwen3-0.6B2026.05 | 79.7 | — | — | |
| BaseBase Model=Qwen3-0.6B2026.05 | 79.03 | — | — | |
| TESSYBase Model=Qwen3-0.6B2026.05 | 79 | — | — | |
| DARTBase Model=Qwen2.5-0.5B-Instruct2026.05 | 61.45 | — | — | |
| GRPOBase Model=Qwen2.5-0.5B-Instruct2026.05 | 56.4 | — | — | |
| Original-SFTBase Model=Qwen2.5-0.5B-Instruct2026.05 | 56.17 | — | — | |
| STaRBase Model=Qwen2.5-0.5B-Instruct2026.05 | 55.2 | — | — | |
| BaseBase Model=Qwen2.5-0.5B-Instruct2026.05 | 53.95 | — | — | |
| TESSYBase Model=Qwen2.5-0.5B-Instruct2026.05 | 47.8 | — | — |