Formal Theorem Proving on FormalML Hard
11.2Proof Length
GPT-5.3-Codex
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.04 | 11.2 | |
2026.04 | 23.3 | |
2026.04 | 27.5 | |
2026.04 | 31.6 | |
2026.04 | 32.8 | |
2026.04 | 39.7 |
GPT-5.3-Codex
| Method | Links | |
|---|---|---|
2026.04 | 11.2 | |
2026.04 | 23.3 | |
2026.04 | 27.5 | |
2026.04 | 31.6 | |
2026.04 | 32.8 | |
2026.04 | 39.7 |