Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
80.28Accuracy
10
May 26, 2026
77.5Accuracy
10
May 26, 2026
2.6Average Rank
10
May 26, 2026
49BLEU Score
10
May 26, 2026
88.25Accuracy (Non-Adv)
10
May 22, 2026
0.277BLEU-1
10
May 20, 2026
5.1BLEU-1
10
May 20, 2026
24.2BLEU-1
10
May 20, 2026
25.61Mean F1 Score
10
May 20, 2026
39.6F1 Score
10
May 19, 2026
67.1Exact Match (EM)
10
May 19, 2026
70.3EM
10
May 19, 2026
78.1Accuracy
10
May 15, 2026
35LLM-as-a-Judge Score
10
May 14, 2026
0.33LLM-as-a-Judge Score
10
May 14, 2026
0.58LLM-as-a-Judge Score
10
May 14, 2026
73LLM Judge Score
10
May 14, 2026
80LLM-as-a-Judge Score
10
May 14, 2026
80LLM-as-a-Judge Score
10
May 14, 2026
26.1F1 Score
10
May 12, 2026
66.3Accuracy
10
May 8, 2026
81.6True*Info Score (TQA)
10
May 8, 2026
61.3QA EM
10
May 7, 2026
162.54Decoding Speed (tokens/s)
10
May 4, 2026
55.321Accuracy
10
Apr 28, 2026