Fj
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
- 37.03best: 89.3 (human)
- 56.61best: 91.2 (human)
- Consistency63.96best: 98.4 (human)
- Distribution28.4best: 93.08 (GlobalPrior)
- 19.74best: 87.4 (human)
- Plausibility85.12best: 97.2 (human)
- 95.76best: 98.9 (human)