Extrapolative Generalization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
126.33Mean Reward
5
Mar 10, 2026
120.23Mean Reward
5
Mar 10, 2026
231.73Mean Reward
5
Mar 10, 2026
499.91Mean Reward
5
Mar 10, 2026
967.64Mean Reward
5
Mar 10, 2026
321.9Mean Reward
5
Mar 10, 2026
91Success Rate
3
Mar 10, 2026
80Success Rate
3
Mar 10, 2026