Theorem Proving on Putnam 2025 (full)
631Problem A1 ScoreSEED-PROVER 1.5
Evaluation results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| SEED-PROVER 1.52026.01 | 631 | 469 | 927 | 1,095 | — | 881 | 849 | 1,613 | 584 | 628 | 2,499 | 2,594 | |
| AXIOM2026.01 | 556 | 458 | 1,089 | 825 | 1,878 | 468 | 1,179 | 346 | 302 | 993 | 1,310 | 862 | |
| NUMINA-LEAN-AGENT2026.01 | 365 | 401 | 422 | 605 | 3,263 | 835 | 328 | 690 | 292 | 648 | 929 | 1,820 | |
| AXIOM2026.01 | 110 | 180 | 165 | 107 | 518 | 259 | 270 | 65 | 43 | 112 | 254 | 494 | |
| NUMINA-LEAN-AGENTparallelization=None, internet_search=Disabled2026.01 | 97 | 30 | 44 | 169 | 2,040 | 89 | 55 | 142 | 30 | 308 | 88 | 797 | |
| SEED-PROVER 1.52026.01 | 60 | 30 | 120 | 240 | — | 240 | 540 | 360 | 30 | 120 | 240 | 180 | |
| ARISTOTLE2026.01 | 45 | 195 | 103 | 291 | — | 123 | 223 | 108 | 70 | — | 291 | 280 | |
| ARISTOTLE2026.01 | 30 | 60 | 30 | 180 | — | 60 | 150 | 25 | 40 | — | 420 | 180 |