List your company

User-aligned task completion on KitchenAmbig (OOD)

87.3AccuracyAdaptive CLIPR
80.22882.06483.985.736May 12, 2026

Evaluation results

MethodLinks
Adaptive CLIPRLLM engine=Claude Sonnet 4.5, alpha=1.5, f=52026.0587.3
GATELLM engine=Claude Sonnet 4.52026.0585.3
CIPHERLLM engine=Claude Sonnet 4.52026.0580.5