List your company

LLM response quality prediction on ID Claude 3.5 Haiku 20241022 (test)

0.45RMSEMIRT-Router
0.44320.48910.5350.5809Jun 1, 2025

Evaluation results

MethodLinks
MIRT-Routeralpha=0.8, Target LLM=Claude 3.5 Haiku, scenario=ID2025.060.450.436267
NIRT-Routeralpha=0.8, Target LLM=Claude 3.5 Haiku, scenario=ID2025.060.450.426268
RouterBenchalpha=0.8, Target LLM=Claude 3.5 Haiku, scenario=ID2025.060.620.555034