Reasoning on BBH (Accuracy and Loss)
41.9BBH AccuracyMuon
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MuonOptimizer=Muon, Model Size=3B2026.04 | 41.9 | 1.502 | |
| AdamWOptimizer=AdamW, Model Size=3B2026.04 | 36.6 | 1.534 | |
| Adam+NexusOptimizer=Adam+Nexus, Model Size=3B2026.04 | 36.6 | 1.504 |