Multi-agent task completion
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
98Math Score
14
Apr 2, 2026
56.3Completion Rate
3
Feb 26, 2026
97.5Completion Rate
3
Feb 26, 2026
100Completion Rate
3
Feb 26, 2026
—
—Primary metric
0
Apr 8, 2026
—
—Primary metric
0
Apr 8, 2026
—
—Primary metric
0
Apr 8, 2026
—
—Primary metric
0
Apr 8, 2026