List your company

Question Answering on BBH Disambiguation QA

71Accuracy (BBH Disambiguation QA)TextGrad
55.459.4563.567.55Nov 25, 2025

Evaluation results

MethodLinks
TextGradBackbone=GPT-4o, Optimization Type=Template2025.1171
evaluation-instructed prompt optimizationBackbone=GPT-4o, Optimization Type=Query-dependent2025.1169
APEBackbone=GPT-4o, Optimization Type=Template2025.1167
Self-RefineBackbone=LLaMA-3.1, Optimization Type=Query-dependent2025.1166
evaluation-instructed prompt optimizationBackbone=LLaMA-3, Optimization Type=Query-dependent2025.1165
Self-RefineBackbone=LLaMA-3, Optimization Type=Query-dependent2025.1165
evaluation-instructed prompt optimizationBackbone=LLaMA-3.1, Optimization Type=Query-dependent2025.1165
TextGradBackbone=LLaMA-3.1, Optimization Type=Template2025.1165
TextGradBackbone=LLaMA-3, Optimization Type=Template2025.1164
LLM onlyBackbone=LLaMA-3.1, Optimization Type=None2025.1164
Pro-RefineBackbone=LLaMA-3.1, Optimization Type=Query-dependent2025.1164
LLM onlyBackbone=LLaMA-3, Optimization Type=None2025.1163
Pro-RefineBackbone=LLaMA-3, Optimization Type=Query-dependent2025.1163
APEBackbone=LLaMA-3, Optimization Type=Template2025.1163
APEBackbone=LLaMA-3.1, Optimization Type=Template2025.1163
Pro-RefineBackbone=GPT-4o, Optimization Type=Query-dependent2025.1163
LLM onlyBackbone=GPT-4o, Optimization Type=None2025.1158
Self-RefineBackbone=GPT-4o, Optimization Type=Query-dependent2025.1156