Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
18.77Accuracy
12
May 26, 2026
47.62Accuracy
12
May 26, 2026
66.08Accuracy
12
May 26, 2026
24.25Accuracy
12
May 26, 2026
93.8Accuracy
12
May 26, 2026
271.87TTFT (ms)
12
May 26, 2026
233.2TTFT (ms)
12
May 26, 2026
355.12TTFT (ms)
12
May 26, 2026
204TTFT (ms)
12
May 26, 2026
0.66Peak GPU memory (GB)
12
May 26, 2026
0.53Peak GPU Memory (GB)
12
May 26, 2026
0.58Peak GPU Memory (GB)
12
May 26, 2026
0.66Peak GPU Memory (GB)
12
May 26, 2026
70ASR Score (Before)
12
May 25, 2026
100True WS Score
12
May 25, 2026
5.9Error Rate (ER)
12
May 21, 2026
17.2F1 Score
12
May 19, 2026
90.2Accuracy
12
May 18, 2026
75.5Accuracy (Acc)
12
May 13, 2026
0.75Cohen's d
12
May 13, 2026
0.945Cohen's d
12
May 13, 2026
0.803Cohen's d
12
May 13, 2026
1.089Cohen's d
12
May 13, 2026
0.518Spearman's rho
12
May 13, 2026
0.636Spearman's rho
12
May 13, 2026