List your company

Math Generation on GSM8K (Pass@1, GSS@10)

70.58Pass@1GRPO-MA
62.218464.389266.5668.7308Sep 29, 2025

Evaluation results

MethodLinks
GRPO-MATN=4, AN=4, S/S=132.872025.0970.585
GRPOTN=16, AN=1, S/S=225.432025.0965.1315
GRPOTN=8, AN=1, S/S=140.052025.0964.6713
GRPOTN=4, AN=1, S/S=111.242025.0962.545