Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
70.1LLM-Judge Accuracy
9
Jun 4, 2026
72LLM-judge Accuracy
9
Jun 4, 2026
54.9LLM-judge Accuracy
9
Jun 4, 2026
50.6F1
9
Jun 4, 2026
43.81F1 Score
9
Jun 4, 2026
37.45F1 Score
9
Jun 4, 2026
37.39F1 Score
9
Jun 4, 2026
37.18F1 Score (F1)
9
Jun 4, 2026
96PU Score
9
Jun 2, 2026
80.7Accuracy
9
Jun 2, 2026
42.83Accuracy (ARC-C)
9
Jun 1, 2026
61.08Macro-F1
9
May 27, 2026
87.4Accuracy
9
May 26, 2026
100AR (%)
9
May 21, 2026
100AR (%)
9
May 21, 2026
37.83F1 Score
9
May 21, 2026
61.47F1 Score
9
May 21, 2026
70.69F1 Score
9
May 21, 2026
90Exact Match Accuracy
9
May 21, 2026
99Exact Match Accuracy
9
May 21, 2026
100Exact Match Accuracy
9
May 21, 2026
100Exact Match Accuracy
9
May 21, 2026
100EM Accuracy
9
May 21, 2026
0.066Mean Improvement
9
May 18, 2026
82.83ARC-E Accuracy
9
May 18, 2026