List your company

Question Answering on IndiRef Spot the difference

42Temporal Accuracy (FEM)Qwen QwQ - 32B
17.0423.523036.48Jan 14, 2026

Evaluation results

MethodLinks
Qwen QwQ - 32BContext=Full Dialog History2026.014234262226202820
Llama3.1 - 8BContext=Full Dialog History2026.014038303236362616
Gemma2 - 27BContext=Full Dialog History2026.014030282032262612
Gemma2 - 9BContext=Full Dialog History2026.013420241628162010
Gemma2 - 2BContext=Full Dialog History2026.011812181020121610