Code Verification on VERINA
176Success CountIDS
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| IDSmodality=concurrent code-and-proof2026.05 | 176 | — | — | |
| Claude Codemodality=concurrent code-and-proof2026.05 | 149 | — | — | |
| Codexmodality=concurrent code-and-proof2026.05 | 136 | — | — | |
| Qwen2.5 CoderPrompting Strategy=Functional, Setting=pass@12025.11 | 60 | — | 4.8 | |
| Qwen2.5 CoderPrompting Strategy=Direct, Setting=pass@12025.11 | 51 | — | — | |
| Prior SOTAmodality=concurrent code-and-proof2026.05 | 38 | — | — | |
| Base GoedelPrompting Strategy=Direct, Setting=pass@12025.11 | 14 | — | — | |
| Base GoedelPrompting Strategy=Functional, Setting=pass@12025.11 | 12 | — | -1.1 |