Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.009MAE
2
Feb 26, 2026
0.005MAE
2
Feb 26, 2026
0.007MAE
2
Feb 26, 2026
81.72Accuracy
2
Feb 26, 2026
48.47Accuracy
2
Feb 26, 2026
49.1Accuracy
2
Feb 26, 2026
31.3EM
2
Feb 26, 2026
29.7EM
2
Feb 26, 2026
59.7EM
2
Feb 26, 2026
40.3EM
2
Feb 26, 2026
69.4Accuracy
2
Feb 26, 2026
681,322Resp. Tokens
2
Feb 26, 2026
98.9Accuracy
2
Feb 26, 2026
91.184Accuracy
2
Feb 26, 2026
74.4F1 Score
2
Feb 26, 2026
42.5Win Ratio
2
Feb 26, 2026
56.5Win Ratio
2
Feb 26, 2026
64Win Ratio
2
Feb 26, 2026
77.6Exact Match
2
Feb 26, 2026
40.02Exact Match
2
Feb 26, 2026
95.1Accuracy
2
Feb 26, 2026
87Exact Match Accuracy
2
Feb 26, 2026
100Exact Match Accuracy
2
Feb 26, 2026
0.275F1 Score
2
Feb 26, 2026
80.7Accuracy
2
Feb 26, 2026