| 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,,,,61.50,42.40,9.90,16.90,40.50,17.7,, | |
| 10,,,,75.40,57.00,18.80,22.20,44.40,20.0,, | |
| 20,,,,79.80,57.40,24.60,24.30,45.90,21.8,, | |
| 30,,,,80.10,59.40,22.10,27.30,51.00,24.2,, | |
| 40,,,,81.30,64.80,27.20,28.60,54.80,28.1,, | |
| 50,,,,81.90,65.20,26.80,27.60,56.70,24.8,, | |
| 60,,,,83.10,64.80,29.00,27.60,58.10,25.5,, | |
| 70,,,,82.30,64.40,28.30,27.10,60.00,25.7,, | |
| 80,,,,81.60,65.80,28.30,29.20,60.20,27.0,, | |
| 90,,,,82.90,66.00,29.00,29.90,61.10,27.4,, | |
| 100,,,,83.50,65.60,29.40,30.10,63.00,28.5,, | |