| 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,,,,59.90,46.60,14.00,18.70,40.30,21.1,24.7,21.0 | |
| 10,27.80,4.30,3.50,74.00,54.00,18.80,22.80,43.90,20.3,54.3,45.3 | |
| 20,31.20,6.10,2.60,78.20,57.80,25.40,24.70,45.50,20.3,55.7,47.5 | |
| 30,33.80,5.90,2.70,80.10,60.40,22.40,25.00,47.90,20.9,56.8,47.2 | |
| 40,36.40,6.60,3.90,79.90,65.00,23.50,24.70,50.70,21.3,57.6,48.6 | |
| 50,36.60,5.90,3.60,81.20,64.20,25.70,24.60,53.70,25.1,58.4,49.6 | |
| 60,38.00,6.70,3.80,81.30,63.60,28.30,26.70,56.00,24.0,60.0,50.3 | |
| 70,35.30,8.00,4.00,82.30,61.80,26.50,28.10,55.50,26.2,60.8,50.9 | |
| 80,36.10,7.20,3.30,82.00,64.40,24.30,26.40,59.40,25.0,61.6,51.2 | |
| 90,35.00,7.80,4.20,82.60,64.40,26.50,25.50,60.70,24.4,60.5,51.5 | |
| 100,36.20,8.80,5.00,82.00,65.20,29.40,28.30,60.70,24.2,60.6,52.2 | |