Long-horizon Reasoning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
65.59Sobj Score
6
Jul 3, 2026
59.37Sobj Score
6
Jul 3, 2026
66.71Sobj Score
6
Jul 3, 2026
66.12Object Score
6
Jul 3, 2026
73.9Average Score
6
May 12, 2026
100Performance (n=13)
3
Mar 10, 2026
100Performance (n=11)
3
Mar 10, 2026