Mathematical Reasoning on GSM8K (Accuracy, Exit Position)
78.2AccuracyBackbone
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BackboneBackbone Model=Llama3.1 8B (32 layers)2026.04 | 78.2 | — | |
| River-LLMBackbone Model=Llama3.1 8B (32 layers), Threshold (τ)=0.72026.04 | 75.6 | 26.98 | |
| River-LLMBackbone Model=Llama3.1 8B (32 layers), Threshold (τ)=0.52026.04 | 74.4 | 2.96 | |
| BackboneBackbone Model=Llama3.2 1B (16 layers)2026.04 | 33.5 | — | |
| River-LLMBackbone Model=Llama3.2 1B (16 layers), Threshold (τ)=0.72026.04 | 33.5 | 15.05 | |
| River-LLMBackbone Model=Llama3.2 1B (16 layers), Threshold (τ)=0.52026.04 | 29.3 | 3.79 |