Codex (Self-Evaluation Guided Decoding, PAL, multiple reasoning chains, 9-shot gen, 5-shot eval)
Reported on 1 benchmark across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Reasoning1 result
- Accuracy85.5best: 97.72 (Claude 3.5 Sonnet (HPT))