List your company

Reasoning on BBH subset

47.2AccuracyTUR-DPO
43.76844.65945.5546.441Apr 30, 2026

Evaluation results

MethodLinks
TUR-DPOEvaluation Protocol=Human eval2026.0447.2
TUR-DPOEvaluation Protocol=LLM judge2026.0446.7
PPOEvaluation Protocol=Human eval2026.0446
DPOEvaluation Protocol=Human eval2026.0444.5
IPOEvaluation Protocol=LLM judge2026.0444.3
DPOEvaluation Protocol=LLM judge2026.0443.9