Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
40.6Accuracy
31
Jul 3, 2026
50.52Qwen2.5-3B-Instruct F1
31
Jun 12, 2026
68.81GPT Accuracy
31
Jun 16, 2026
76.2Accuracy
31
Feb 26, 2026
70.2Accuracy
30
May 22, 2026
91.7F1 Score
30
May 22, 2026
80.6Accuracy
30
May 15, 2026
84.5Accuracy (alpha=0.10)
30
May 15, 2026
35.25F1 Score
30
May 8, 2026
82.77Accuracy
30
Apr 15, 2026
23.62Accuracy
30
Jun 16, 2026
81ASR
30
Apr 10, 2026
85ASR
30
Apr 10, 2026
90ASR
30
Apr 10, 2026
92.71-hop EM@1
30
Apr 1, 2026
85.8EM@1
30
Apr 1, 2026
75Exact Match (EM)
30
Apr 1, 2026
85.67Accuracy
30
Mar 25, 2026
60Accuracy
30
Mar 25, 2026
59.9F1 Score
30
Mar 25, 2026
46F1 Score
30
Feb 26, 2026
60F1 Score
30
Feb 26, 2026
78F1 Score
30
Feb 26, 2026
80Accuracy
30
Feb 26, 2026
26ACC
30
Feb 26, 2026