Close
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
70.8Success Rate
4
May 5, 2026
60Success Rate (Instance 1)
3
Jun 12, 2026
70Close Success Rate (Instance 1)
3
Jun 12, 2026
70Success Rate (Instance 1)
3
Jun 12, 2026
9Success Rate
3
Apr 28, 2026
—
—Primary metric
0
Feb 26, 2026