Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
4.49GenericJudge Score
4
Apr 8, 2026
16Exact Match
4
Apr 7, 2026
64.77Accuracy
4
Apr 3, 2026
85.4EM
4
Apr 3, 2026
48.11Mean Faithfulness Score
4
Apr 1, 2026
38.23FC Mean
4
Apr 1, 2026
701Prompt Tokens
4
Mar 31, 2026
59Accuracy (General)
4
Mar 27, 2026
29.3pass@1
4
Mar 26, 2026
1.988R@1
4
Mar 26, 2026
3.497R@1
4
Mar 26, 2026
3.337Recall@1
4
Mar 26, 2026
3.212R@1
4
Mar 26, 2026
4.547R@1
4
Mar 26, 2026
4.051R@1
4
Mar 26, 2026
3.756R@1
4
Mar 26, 2026
2.886Recall@1
4
Mar 26, 2026
0.67Latency (s)
4
Mar 24, 2026
86.09Accuracy
4
Mar 20, 2026
59.4Answer Accuracy
4
Mar 19, 2026
79.98Answer Accuracy
4
Mar 19, 2026
47.9Accuracy
4
Mar 18, 2026
84.8Normalized Log Accuracy
4
Mar 18, 2026
65.5Compressed Accuracy
4
Mar 18, 2026
77.2Normalized Log Accuracy
4
Mar 18, 2026