Mathematical Reasoning on MMLU Out of Domain
1,896.9MTL ScoreFARL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FARLBackbone=R1-Llama-8B, Training Time=4h 26m 4s2025.09 | 1,896.9 | 75.7 | |
| RL (GRPO)Backbone=R1-Llama-8B, Training Time=4h 6m 27s2025.09 | 1,844.4 | 74.5 | |
| R1-Llama-8B (Base)Backbone=R1-Llama-8B2025.09 | 1,386.2 | 71.6 | |
| SFTBackbone=R1-Llama-8B, Training Time=10m 21s2025.09 | 1,207.3 | 73.2 |