General AI Assistant Tasks
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
93.2Accuracy
291
May 18, 2026
80.61Avg Performance
77
Jun 9, 2026
83.4Pass@1 Score
38
May 19, 2026
71.5Task Success Rate
30
May 13, 2026
33.3Internalized Inference Rate
26
Jun 4, 2026
73.93Average Accuracy
23
Apr 23, 2026
88.5Avg@8 Score
22
Apr 23, 2026
37.5Performance
15
Feb 26, 2026
59.3Perf (%)
15
Feb 26, 2026
83.02Performance (%)
15
Feb 26, 2026
63.19Performance (%)
15
Feb 26, 2026
47Accuracy
14
Apr 20, 2026
43.7Score
14
Feb 26, 2026
62.1Accuracy (Text)
8
Jul 1, 2026
42.9Success Rate
8
May 12, 2026
66.7Success Rate
8
May 12, 2026
63.11Pass@3
8
Feb 26, 2026
57.14Accuracy
8
Feb 26, 2026
67.6Accuracy
7
May 15, 2026
44.2Accuracy
2
Feb 26, 2026
54.2Accuracy
2
Feb 26, 2026
62.3Accuracy
2
Feb 26, 2026