Automated Theorem Proving
The goal of Automated Theorem Proving is to automatically generate a proof, given a conjecture (the target theorem) and a knowledge base of known facts, all expressed in a formal language. Automated Theorem Proving is useful in a wide range of applications, including the verification and synthesis of software and hardware systems.
Source: Learning to Prove Theorems by Learning to Generate Theorems
Papers
Showing 1–10 of 288 papers
All datasetsminiF2F-testminiF2F-validHolStep (Conditional)HOList benchmarkHolStep (Unconditional)Metamath set.mmminiF2F-curriculumCompCertCoqGym
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Kimina-Prover-Preview | cumulative | 80.74 | — | Unverified |
| 2 | ProofAug | cumulative | 66 | — | Unverified |
| 3 | DeepSeek-Prover-V1.5 | cumulative | 63.5 | — | Unverified |
| 4 | Subgoal-XL | cumulative | 56.1 | — | Unverified |
| 5 | DeepSeek-Prover | cumulative | 52 | — | Unverified |
| 6 | LEGO-Prover ChatGPT | cumulative | 47.1 | — | Unverified |
| 7 | Lyra + GPT-4 | cumulative | 47.1 | — | Unverified |
| 8 | Decomposing the Enigma | cumulative | 45.5 | — | Unverified |
| 9 | Evariste | cumulative | 41 | — | Unverified |
| 10 | Evariste-7d | cumulative | 40.6 | — | Unverified |