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

Mathematical Reasoning on GSM8K (HS, FA)

38.24Hit Score (HS)

Vaccine

-0.88489.272619.4329.5874Feb 28, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
38.2454.37
2026.02
32.0556.73
2026.02
26.6742.76
2026.02
23.9410.9
2026.02
23.611.7
2026.02
23.5144.1
2026.02
22.1358.97
2026.02
18.1762.2
2026.02
14.5464.66
2026.02
13.0254.97
2026.02
11.1347.96
2026.02
9.0616.27
2026.02
7.642.7
2026.02
5.869.23
2026.02
3.9163.9
2026.02
2.1968.63
2026.02
1.2415.07
2026.02
0.9246.6
2026.02
0.9157.43
2026.02
0.6267.3