Formal Theorem Proving on miniF2F rw (test)
75Pass@8Goedel-Prover-V2-8B
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Goedel-Prover-V2-8BVariant=controlled2026.05 | 75 | 78.3 | — | — | 77 | |
| Goedel-Prover-V2-8BVariant=seed2026.05 | 74.6 | 77.5 | — | 58.9 | 76.4 | |
| Goedel-Prover-V2-8BVariant=test-time2026.05 | 74.4 | 78.6 | — | — | 76.7 | |
| Goedel-Prover-V2-8BVariant=random2026.05 | 72.9 | 76.7 | — | 56 | 75.3 | |
| DeepSeek-Prover-V2-7BVariant=seed2026.05 | 71 | 75 | — | 58 | 73.2 | |
| DeepSeek-Prover-V2-7BVariant=test-time2026.05 | 70.9 | 74.2 | — | — | 72.9 | |
| DeepSeek-Prover-V2-7BVariant=controlled2026.05 | 70.3 | 74.2 | — | — | 72.3 | |
| Kimina-Prover-Distill-8BVariant=test-time2026.05 | 70.1 | 74.4 | — | — | 72.6 | |
| Kimina-Prover-Distill-8BVariant=controlled2026.05 | 68.8 | 72.5 | — | — | 71 | |
| DeepSeek-Prover-V2-7BVariant=random2026.05 | 68.5 | 73 | — | 53.4 | 70.8 | |
| Kimina-Prover-Distill-8BVariant=seed2026.05 | 68.2 | 71.3 | — | 55 | 70 | |
| Kimina-Prover-Distill-8BVariant=random2026.05 | 66.5 | 70.7 | — | 52.2 | 68.9 | |
| DeepSeek-Prover-V2-7BVariant=controlled2026.05 | 64 | 67.3 | 68.8 | — | — | |
| DeepSeek-Prover-V2-7BVariant=test-time2026.05 | 62.6 | 66 | 67.6 | — | — | |
| DeepSeek-Prover-V2-7BVariant=seed2026.05 | 61.7 | 64.6 | 66.8 | — | — | |
| DeepSeek-Prover-V2-7BVariant=random2026.05 | 59.7 | 63.2 | 64.8 | — | — | |
| Goedel-Prover-DPOVariant=seed2026.05 | 52.9 | 57.7 | 59 | — | — | |
| Goedel-Prover-DPOVariant=controlled2026.05 | 52.6 | 57.9 | 59.9 | — | — | |
| Goedel-Prover-SFTVariant=seed2026.05 | 51.7 | 56.5 | 57.8 | — | — | |
| Goedel-Prover-SFTVariant=test-time2026.05 | 50.5 | 56 | 57.6 | — | — | |
| Goedel-Prover-SFTVariant=controlled2026.05 | 50 | 55.7 | 57.4 | — | — | |
| Goedel-Prover-DPOVariant=random2026.05 | 49.5 | 54.7 | 56.4 | — | — | |
| Goedel-Prover-DPOVariant=test-time2026.05 | 49.1 | 55.5 | 57.1 | — | — | |
| Goedel-Prover-SFTVariant=random2026.05 | 47.4 | 53.3 | 55.2 | — | — |