ResearchBenchmarks20 Questions on 20Q CommonFollow10Worst Case Interaction LengthGoT9.84810.87411.912.926Feb 2, 2026Evaluation ResultsMethodMethodLinksWorst Case Interaction LengthGoTBackbone=Qwen 2.5 72B...Backbone=Qwen 2.5 72B Instruct2026.0210GoTBackbone=GPT 4.1Backbone=GPT 4.12026.0210.2UoTBackbone=GPT 4.1Backbone=GPT 4.12026.0211UoTBackbone=Qwen 2.5 72B...Backbone=Qwen 2.5 72B Instruct2026.0211DPBackbone=Qwen 2.5 72B...Backbone=Qwen 2.5 72B Instruct2026.0212.7DCBackbone=Qwen 2.5 72B...Backbone=Qwen 2.5 72B Instruct2026.0212.7DCBackbone=GPT 4.1Backbone=GPT 4.12026.0212.9DPBackbone=GPT 4.1Backbone=GPT 4.12026.0213.8