Mathematical Reasoning on MATH500 (vbal)
0.778VBAL ScoreBase
Evaluation Results
| Method | Links | |
|---|---|---|
| BaseModel=Tulu3.1-8B2026.04 | 0.778 | |
| BaseModel=Llama3.1-8B2026.04 | 0.763 | |
| BaseModel=OLMo2-7B2026.04 | 0.734 | |
| Reflect-and-rephraseModel=OLMo2-7B2026.04 | 0.061 | |
| Reflect-and-rephraseModel=Llama3.1-8B2026.04 | 0.04 | |
| STRUCT.Model=OLMo2-7B2026.04 | 0.03 | |
| PROF.Model=Llama3.1-8B2026.04 | 0.028 | |
| PROF.Model=OLMo2-7B2026.04 | 0.026 | |
| Reflect-and-rephraseModel=Tulu3.1-8B2026.04 | 0.024 | |
| SIMPL.Model=OLMo2-7B2026.04 | 0.02 | |
| STRUCT.Model=Llama3.1-8B2026.04 | 0.012 | |
| SIMPL.Model=Llama3.1-8B2026.04 | 0.002 | |
| PROF.Model=Tulu3.1-8B2026.04 | -0.003 | |
| STRUCT.Model=Tulu3.1-8B2026.04 | -0.01 | |
| SIMPL.Model=Tulu3.1-8B2026.04 | -0.017 |