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

Generalization Evaluation on AM-Thinking Distilled-math&code v1 (Unseen)

49.55Average Unseen Score

Equal

21.449228.744636.0443.3354Jul 1, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.07
49.55
2026.07
49.09
2026.07
48.98
2026.07
48.12
2026.07
48
2026.07
47.98
2026.07
46.94
2026.07
46.37
2026.07
46.19
2026.07
41.46
2026.07
28.6
2026.07
27.08
2026.07
26.93
2026.07
26.49
2026.07
26.24
2026.07
26.08
2026.07
26.07
2026.07
25.9
2026.07
25.84
2026.07
25.69
2026.07
25.64
2026.07
25.51
2026.07
25.36
2026.07
25.04
2026.07
25.02
2026.07
24.88
2026.07
24.71
2026.07
24.43
2026.07
24.26
2026.07
24.12
2026.07
23.59
2026.07
23.45
2026.07
23.42
2026.07
22.82
2026.07
22.53