Data Analysis
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
79.55GPT Score
60
Mar 11, 2026
81.32Pass@1
21
Mar 16, 2026
92.82Accuracy
13
Feb 26, 2026
37.04Accuracy
13
Feb 26, 2026
83.33Accuracy
13
Feb 26, 2026
63.68Accuracy
13
Feb 26, 2026
45.24Accuracy
12
Feb 26, 2026
87.5Accuracy
12
Feb 26, 2026
26.63Accuracy
10
May 21, 2026
43.92Helpfulness
10
Feb 26, 2026
50.79Helpfulness
10
Feb 26, 2026
90.2Accuracy
8
Jun 18, 2026
96Correctness
7
May 8, 2026
45Avg@3
5
Feb 26, 2026
62.04Pass@1
4
Mar 16, 2026
92.5Task Completion Rate
4
Feb 26, 2026