Conditional Hypothesis Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
71.6Surface Similarity
9
Jun 4, 2026
73Surface Similarity
9
Jun 4, 2026
0.737Surface Similarity
9
Jun 4, 2026
75Surface Similarity
9
Jun 4, 2026
3.25Helpfulness
4
Jun 4, 2026
3Helpfulness
2
Jun 4, 2026