Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
87Accuracy (ARC-E)
11
Jul 3, 2026
64.5Accuracy
11
Jun 18, 2026
56.57Containment Acc.
11
Jun 17, 2026
64.65GPT Accuracy
11
Jun 17, 2026
32.3Containment Accuracy
11
Jun 17, 2026
71.2Containment Accuracy
11
Jun 17, 2026
66.3Containment Accuracy
11
Jun 17, 2026
37.44Average@32
11
Jun 16, 2026
0.89Pearson r
11
Jun 12, 2026
0.94Pearson r
11
Jun 12, 2026
0.96Pearson r
11
Jun 12, 2026
0.94Pearson r
11
Jun 12, 2026
50.2Accuracy
11
Jun 11, 2026
74.3EM
11
Jun 5, 2026
39.6Accuracy
11
Jun 4, 2026
38Accuracy
11
Jun 4, 2026
37.6EM
11
Jun 2, 2026
65.31Accuracy
11
Jun 1, 2026
31.67Accuracy
11
Jun 1, 2026
88.1Accuracy
11
Jun 1, 2026
13.57Brier Score
11
Jun 1, 2026
56.3Score
11
May 26, 2026
87.9Accuracy (Non-Adversarial)
11
May 22, 2026
38.92Episode-Level Accuracy
11
May 22, 2026
37.24Episode-level QA Accuracy
11
May 22, 2026