Mathematical Reasoning on GSM8K, MATH, AIME24, Minerva, Olympiad
73.3MATH ScoreDataFlow-SFT-15K(filtered)
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| DataFlow-SFT-15K(filtered)Data Source=DataFlow-SFT-15K, Filtering Method=DataFlow SFT pipeline, SFT Data Scale=15K2025.12 | 73.3 | 90.2 | 13.3 | 36 | 35.9 | 49.7 | |
| DataFlow-SFT-15K(random)Data Source=DataFlow-SFT-15K, Filtering Method=random, SFT Data Scale=15K2025.12 | 72.6 | 89.6 | 13.3 | 37.9 | 32.9 | 49.3 | |
| WizardLM(filtered)Data Source=WizardLM, Filtering Method=DataFlow SFT pipeline, SFT Data Scale=5K2025.12 | 69.7 | 88.8 | 10 | 19.9 | 35.4 | 44.8 | |
| WizardLM(random)Data Source=WizardLM, Filtering Method=random, SFT Data Scale=5K2025.12 | 61.1 | 84.2 | 6.7 | 18 | 29.3 | 39.9 | |
| Alpaca(filtered)Data Source=Alpaca, Filtering Method=DataFlow SFT pipeline, SFT Data Scale=5K2025.12 | 60.3 | 80 | 13.3 | 14.7 | 30.7 | 39.8 | |
| Alpaca(random)Data Source=Alpaca, Filtering Method=random, SFT Data Scale=5K2025.12 | 54.9 | 77.2 | 13.3 | 14 | 27 | 37.3 |