Factual Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
39.33MCQ Accuracy
18
Mar 31, 2026
3.21Accuracy
8
Jun 23, 2026
30Baseline Wins
2
Mar 19, 2026
12Baseline Wins
2
Mar 19, 2026
16Baseline Wins
2
Mar 19, 2026
3Baseline Wins
2
Mar 19, 2026
4Baseline Wins
2
Mar 19, 2026