| 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,,,,61.70,49.00,15.40,16.70,40.10,18.9,, | |
| 10,,,,74.50,55.40,20.60,24.30,43.30,21.1,, | |
| 20,,,,79.50,61.80,23.20,22.20,46.50,20.5,, | |
| 30,,,,79.90,62.20,22.40,24.90,48.50,25.7,, | |
| 40,,,,80.20,62.80,27.90,25.30,52.00,24.2,, | |
| 50,,,,80.30,65.40,27.90,28.60,53.40,24.2,, | |
| 60,,,,81.10,65.00,26.10,25.00,54.20,23.8,, | |
| 70,,,,81.00,63.80,28.70,28.30,57.00,26.8,, | |
| 80,,,,81.90,64.40,28.30,28.90,59.00,23.7,, | |
| 90,,,,81.40,66.40,28.70,28.90,59.80,23.7,, | |
| 100,,,,82.20,64.00,27.90,28.40,59.30,26.6,, | |