List your company

Question Answering on ARC-c (Accuracy, Exit Position)

51.5AccuracyBackbone
34.54838.94943.3547.751Apr 20, 2026

Evaluation results

MethodLinks
BackboneBackbone Model=Llama3.1 8B (32 layers)2026.0451.5—
River-LLMBackbone Model=Llama3.1 8B (32 layers), Threshold (τ)=0.72026.0451.28.44
River-LLMBackbone Model=Llama3.1 8B (32 layers), Threshold (τ)=0.52026.0450.33.01
River-LLMBackbone Model=Llama3.2 1B (16 layers), Threshold (τ)=0.72026.0435.910.68
BackboneBackbone Model=Llama3.2 1B (16 layers)2026.0435.7—
River-LLMBackbone Model=Llama3.2 1B (16 layers), Threshold (τ)=0.52026.0435.23.24