Instruction Following on IFEval (pass@1 Strict)
82.4Pass@1 (Strict)EXPERT
Evaluation results
| Method | Links | |
|---|---|---|
| EXPERTBase Model=OLMo-3-7B, Setting=RL Zero, Fine-tuning=RLVR2026.04 | 82.4 | |
| w/o MergingModels=Math2026.02 | 64.93 | |
| REGMEANBase Model=OLMo-3-7B, Setting=RL Zero, Fine-tuning=RLVR2026.04 | 62.8 | |
| ACTMatBase Model=OLMo-3-7B, Setting=RL Zero, Fine-tuning=RLVR2026.04 | 47 | |
| w/o MergingModels=Code2026.02 | 43.05 | |
| SCF-RKLModels=Fuse2026.02 | 42.12 | |
| Task ArithmeticModels=Fuse2026.02 | 38.08 | |
| Dare Task ArithmeticModels=Fuse2026.02 | 37.5 | |
| Dare Ties MergingModels=Fuse2026.02 | 37.25 | |
| Ties MergingModels=Fuse2026.02 | 34.7 | |
| SCEModels=Fuse2026.02 | 34.47 | |
| TSVBase Model=OLMo-3-7B, Setting=RL Zero, Fine-tuning=RLVR, Scaling Factor (alpha)=12026.04 | 34 | |
| TABase Model=OLMo-3-7B, Setting=RL Zero, Fine-tuning=RLVR, Scaling Factor (alpha)=0.42026.04 | 32.2 | |
| AVERAGEBase Model=OLMo-3-7B, Setting=RL Zero, Fine-tuning=RLVR2026.04 | 31.2 | |
| ZERO-SHOTBase Model=OLMo-3-7B, Setting=RL Zero, Fine-tuning=RLVR2026.04 | 30.7 | |
| ISO-CBase Model=OLMo-3-7B, Setting=RL Zero, Fine-tuning=RLVR, Scaling Factor (alpha)=12026.04 | 28.8 |