Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
96.3Accuracy
906
Apr 2, 2026
87.3Accuracy (ARC)
631
Jun 24, 2026
98.2Accuracy
597
Jun 5, 2026
86.5Accuracy
589
Jul 7, 2026
95.23Accuracy
544
Jun 9, 2026
94.4Accuracy
465
Feb 26, 2026
96.4Normalized Acc
420
Jun 8, 2026
95.8F1 Score
380
Apr 6, 2026
94.95Accuracy
347
May 28, 2026
96.07Accuracy
319
Jun 24, 2026
90.9Accuracy
317
Apr 21, 2026
97.2Accuracy
283
Apr 8, 2026
94.1Accuracy
283
Jun 8, 2026
86EM
260
Jul 8, 2026
95.4F1 Score
260
Feb 27, 2026
84.2Accuracy
258
Feb 26, 2026
90.48Accuracy
246
Jul 7, 2026
86.68Accuracy
238
Mar 30, 2026
90.03Accuracy
233
Jun 26, 2026
94.6Accuracy
230
Mar 13, 2026
60EM
227
Jun 29, 2026
89.4F1
215
May 8, 2026
82.48PIQA Accuracy
199
Jun 11, 2026
68.4Accuracy
186
Mar 12, 2026
86.1EM
182
Apr 7, 2026