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

Mathematical Reasoning on GSM8K 8B Instruct (test)

58.6Accuracy

Prob Margin + Both

41.4445.89550.3554.805Apr 12, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.04
58.6
2026.04
56.8
2026.04
55
2026.04
52.6
2026.04
50.9
2026.04
47.2
2026.04
46.6
2026.04
45
2026.04
42.1