Coarse-to-Fine Reasoning, Single Model
Reported on 7 benchmarks across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing7 results
- 72.14best: 89.3 (human)
- 81.16best: 91.2 (human)
- Consistency90.96best: 98.4 (human)
- Distribution2.39best: 93.08 (GlobalPrior)
- 64.19best: 87.4 (human)
- Plausibility84.81best: 97.2 (human)
- 96.77best: 98.9 (human)