Formal Theorem Proving on miniF2F rw (val)
81.1Pass@8Goedel-Prover-V2-8B
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Goedel-Prover-V2-8BVariant=seed2026.05 | 81.1 | 83.2 | — | 68.8 | 82.5 | |
| Goedel-Prover-V2-8BVariant=controlled2026.05 | 80.6 | 82.8 | — | — | 81.9 | |
| Goedel-Prover-V2-8BVariant=test-time2026.05 | 80.4 | 82.8 | — | — | 81.9 | |
| DeepSeek-Prover-V2-7BVariant=test-time2026.05 | 79.7 | 81.1 | 81.5 | — | — | |
| Goedel-Prover-V2-8BVariant=random2026.05 | 79.5 | 82.2 | — | 65.2 | 81.2 | |
| DeepSeek-Prover-V2-7BVariant=seed2026.05 | 78.4 | 79.1 | 79.5 | — | — | |
| DeepSeek-Prover-V2-7BVariant=seed2026.05 | 78.1 | 80.7 | — | 67.4 | 79.7 | |
| DeepSeek-Prover-V2-7BVariant=controlled2026.05 | 77.7 | 81 | — | — | 79.5 | |
| DeepSeek-Prover-V2-7BVariant=test-time2026.05 | 77.5 | 81 | — | — | 79.3 | |
| DeepSeek-Prover-V2-7BVariant=controlled2026.05 | 77.2 | 79.7 | 80.8 | — | — | |
| DeepSeek-Prover-V2-7BVariant=random2026.05 | 75.9 | 79.3 | — | 62.7 | 77.7 | |
| Kimina-Prover-Distill-8BVariant=controlled2026.05 | 74.2 | 78.3 | — | — | 76.5 | |
| Kimina-Prover-Distill-8BVariant=seed2026.05 | 73.4 | 76.6 | — | 61.9 | 75.4 | |
| Kimina-Prover-Distill-8BVariant=test-time2026.05 | 72 | 76.3 | — | — | 74.5 | |
| DeepSeek-Prover-V2-7BVariant=random2026.05 | 71.1 | 74.1 | 75.3 | — | — | |
| Kimina-Prover-Distill-8BVariant=random2026.05 | 70.9 | 75.8 | — | 57.6 | 73.6 | |
| Goedel-Prover-DPOVariant=seed2026.05 | 58.6 | 63.1 | 64.3 | — | — | |
| Goedel-Prover-SFTVariant=seed2026.05 | 57.7 | 62.8 | 64.8 | — | — | |
| Goedel-Prover-DPOVariant=controlled2026.05 | 57.7 | 63.4 | 65.4 | — | — | |
| Goedel-Prover-DPOVariant=test-time2026.05 | 57.7 | 63.5 | 65.2 | — | — | |
| Goedel-Prover-SFTVariant=test-time2026.05 | 56.3 | 62.6 | 63.6 | — | — | |
| Goedel-Prover-SFTVariant=controlled2026.05 | 54.7 | 60.8 | 63.4 | — | — | |
| Goedel-Prover-DPOVariant=random2026.05 | 53.9 | 59.7 | 61.6 | — | — | |
| Goedel-Prover-SFTVariant=random2026.05 | 51.6 | 58.2 | 60.9 | — | — |