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

Action Selection on AdaptSim

66.5Win Rate

BaseCRS (GPT-4o-mini) VS BaseCRS (3.5-turbo)

39.4646.4853.560.52Jun 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
66.527.26.2
2026.06
6527.57.5
2026.06
64.824.810.5
2026.06
63.828.28
2026.06
61.52810.5
2026.06
59.829.610.6
5922.818.2
57.523.519
2026.06
573310
2026.06
56.82716.2
2026.06
52.537.510
52.522.225.2
52.22621.8
51.522.825.8
50.823.226
2026.06
48.535.516
2026.06
43.538.218.2
2026.06
40.547.512