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

State Abstraction on AMA-Bench SA

52.92Success Metric

OPD-Evolver-9B

27.512834.108940.70547.3011Jun 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
52.92
2026.06
51.41
2026.06
48.88
2026.06
48
2026.06
47.2
2026.06
47.04
2026.06
46.59
2026.06
46.19
2026.06
46.11
2026.06
45.63
2026.06
44.67
2026.06
34.9
2026.06
33.49
2026.06
32.73
2026.06
31.81
2026.06
30.97
2026.06
30.37
2026.06
30.01
2026.06
29.73
2026.06
28.49