Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Early-stopping budget estimation on Search-R1, Sokoban, SWE-bench, and Warehouse Aggregate (test)

2.2False-Abort Rate

Claude Opus 4.7

2.0243.2124.45.588May 29, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
2.228.25062
2026.05
2.855.763123
2026.05
3.349.676101
2026.05
4.938.8190140
2026.05
6.664.1183124