ResearchBenchmarks20 Questions on 20Q BreedsFollow6.6Worst Case Interaction LengthGoT6.4927.2217.958.679Feb 2, 2026Evaluation ResultsMethodMethodLinksWorst Case Interaction LengthGoTBackbone=Qwen 2.5 72B...Backbone=Qwen 2.5 72B Instruct2026.026.6GoTBackbone=GPT 4.1Backbone=GPT 4.12026.027.4DPBackbone=GPT 4.1Backbone=GPT 4.12026.027.8DCBackbone=Qwen 2.5 72B...Backbone=Qwen 2.5 72B Instruct2026.027.8UoTBackbone=Qwen 2.5 72B...Backbone=Qwen 2.5 72B Instruct2026.028DPBackbone=Qwen 2.5 72B...Backbone=Qwen 2.5 72B Instruct2026.028UoTBackbone=GPT 4.1Backbone=GPT 4.12026.029DCBackbone=GPT 4.1Backbone=GPT 4.12026.029.3