| global_step,aime24_acc_avg4,aime25_acc_avg4,amc23_acc_avg4,aime24_acc,aime25_acc,amc23_acc,gsm8k_acc,math500_acc,minerva_math_acc,olympiadbench_acc,mmlu_stem_acc,prompt_level_strict_acc_ood,gpqa_pass@1:1_samples_ood | |
| 0,5.00,1.70,21.20,3.30,3.30,27.50,61.50,42.40,9.90,16.90,40.50,17.7,0.28 | |
| 10,4.20,3.30,32.50,0.00,3.30,25.00,75.40,57.00,18.80,22.20,44.40,20.0,0.26 | |
| 20,4.20,2.50,33.10,3.30,3.30,22.50,79.80,57.40,24.60,24.30,45.90,21.8,0.24 | |
| 30,6.70,0.80,37.50,6.70,6.70,30.00,80.10,59.40,22.10,27.30,51.00,24.2,0.29 | |
| 40,7.50,4.20,34.40,6.70,0.00,27.50,81.30,64.80,27.20,28.60,54.80,28.1,0.29 | |
| 50,5.80,4.20,32.50,3.30,3.30,37.50,81.90,65.20,26.80,27.60,56.70,24.8,0.32 | |
| 60,6.70,2.50,33.80,10.00,3.30,37.50,83.10,64.80,29.00,27.60,58.10,25.5,0.28 | |
| 70,7.50,4.20,36.20,6.70,10.00,35.00,82.30,64.40,28.30,27.10,60.00,25.7,0.28 | |
| 80,5.80,5.80,35.00,6.70,0.00,40.00,81.60,65.80,28.30,29.20,60.20,27.0,0.26 | |
| 90,8.30,4.20,39.40,10.00,6.70,40.00,82.90,66.00,29.00,29.90,61.10,27.4,0.26 | |
| 100,9.20,1.70,40.60,3.30,6.70,40.00,83.50,65.60,29.40,30.10,63.00,28.5,0.25 | |