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

Mathematical Reasoning on GSM8k (flexible_extract)

49.96Flexible Extract Score

Baseline

-1.5211.84525.2138.575Feb 26, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.02
49.96
2026.02
48.9
2026.02
48.22
2026.02
47.84
2026.02
47.31
2026.02
45.94
2026.02
42.84
2026.02
36.92
2026.02
36.47
2026.02
34.72
2026.02
33.89
2026.02
33.89
2026.02
33.81
2026.02
32.3
2026.02
27.14
2026.02
26.46
2026.02
25.47
2026.02
24.03
2026.02
23.35
2026.02
23.12
2026.02
19.33
2026.02
13.42
2026.02
13.12
2026.02
13.04
2026.02
12.59
2026.02
11.9
2026.02
11.3
2026.02
6.22
2026.02
5.84
2026.02
5.53
2026.02
5.31
2026.02
4.63
2026.02
4.02
2026.02
2.81
2026.02
0.46