Mathematics on MATH (Accuracy, Exit Position)
48.1AccuracyMinistral3 8B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Ministral3 8BModel Architecture=Ministral3 8B (34 layers), Evaluation Protocol=Backbone2026.04 | 48.1 | — | |
| River-LLMModel Architecture=Ministral3 8B (34 layers), Early-exit threshold (tau)=0.9, Evaluation Protocol=Adaptive2026.04 | 46.6 | 6.18 | |
| River-LLMModel Architecture=Ministral3 8B (34 layers), Early-exit threshold (tau)=0.8, Evaluation Protocol=Adaptive2026.04 | 46.4 | 5.68 | |
| Phi4-miniModel Architecture=Phi4-mini (32 layers), Evaluation Protocol=Backbone2026.04 | 37.4 | — | |
| River-LLMModel Architecture=Phi4-mini (32 layers), Early-exit threshold (tau)=0.9, Evaluation Protocol=Adaptive2026.04 | 35.1 | 13.69 | |
| River-LLMModel Architecture=Phi4-mini (32 layers), Early-exit threshold (tau)=0.8, Evaluation Protocol=Adaptive2026.04 | 33.1 | 5.77 |