| global_step,amc23_acc_avg16,aime24_acc_avg32,aime25_acc_avg32,gsm8k_acc,math500_acc,minerva_math_acc,olympiadbench_acc,mmlu_stem_acc,prompt_level_strict_acc_ood,mbpp_base_pass@1,mbpp_plus_pass@1 | |
| 0,,,,60.10,44.20,10.30,16.00,40.70,17.7,, | |
| 10,,,,73.20,55.60,19.10,22.10,42.40,20.0,, | |
| 20,,,,78.80,60.60,26.50,25.50,46.20,20.0,, | |
| 30,,,,79.60,60.80,26.80,27.00,49.50,22.9,, | |
| 40,,,,80.30,61.80,28.30,26.40,51.80,22.2,, | |
| 50,,,,80.40,65.20,27.60,25.90,54.40,25.5,, | |
| 60,,,,81.70,63.60,29.40,25.50,55.00,24.4,, | |
| 70,,,,80.40,64.60,27.20,29.50,58.40,25.1,, | |
| 80,,,,81.80,63.40,29.40,29.90,57.90,24.0,, | |
| 90,,,,83.30,66.40,29.80,29.60,58.50,25.9,, | |
| 100,,,,82.70,65.20,30.10,30.40,59.10,26.2,, | |