Long-horizon agentic tasks
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
71.3Pass@1
25
Mar 31, 2026
44.4Pass@1
15
Mar 31, 2026
62.5Pass@1
15
Mar 31, 2026
56.1Pass@1
13
Mar 31, 2026
45.8Pass@1
10
Mar 31, 2026
65Pass@1
2
Mar 31, 2026