Mathematical Proof Correctness on First Proof 16 (Expert Evaluation)
36Total Correct Proofs CountRMA
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| RMAProposers (Kp)=3, Verifiers (Kv)=3, Rounds (N)=52026.05 | 36 | — | — | — | 3 | 5 | 8 | 1 | 1 | |
| Aletheia2026.05 | 24 | — | — | — | 2 | 0 | 5 | 1 | 4 | |
| GPT-5.2RIndustrial System=true2026.05 | 20 | — | — | — | 10 | 14 | 3 | 4 | 3 | |
| AgenticR2026.05 | 14 | — | — | — | 5 | 25 | 3 | 2 | 5 | |
| Opus 4.6Industrial System=true2026.05 | 3 | — | — | — | 2 | 39 | 0 | 1 | 9 | |
| GPT-DRIndustrial System=true, Retrieval-Augmented=true2026.05 | 0 | — | — | — | 0 | 44 | 0 | 0 | 10 | |
| Gem-DRIndustrial System=true, Retrieval-Augmented=true2026.05 | 0 | — | — | — | 0 | 44 | 0 | 0 | 10 |