Mathematical Reasoning on MATH (Accuracy + Exit Position)
27AccuracyBackbone
Evaluation results
| Method | Links | ||
|---|---|---|---|
| BackboneBackbone Model=Llama3.1 8B (32 layers)2026.04 | 27 | — | |
| River-LLMBackbone Model=Llama3.1 8B (32 layers), Threshold (τ)=0.52026.04 | 26.6 | 2.81 | |
| River-LLMBackbone Model=Llama3.1 8B (32 layers), Threshold (τ)=0.72026.04 | 25.7 | 13.1 | |
| BackboneBackbone Model=Llama3.2 1B (16 layers)2026.04 | 17.8 | — | |
| River-LLMBackbone Model=Llama3.2 1B (16 layers), Threshold (τ)=0.72026.04 | 17 | 14.67 | |
| River-LLMBackbone Model=Llama3.2 1B (16 layers), Threshold (τ)=0.52026.04 | 14.6 | 3.56 |