ResearchBenchmarksLogical Reasoning on FOLIO (Optimization-phase token usage)Logical Reasoning on FOLIO (Optimization-phase token usage)Follow453Optimization-phase Token UsageETGPO378.32882.411,386.51,890.59Feb 1, 2026Evaluation resultsMethodMethodLinksOptimization-phase Token UsageETGPOBackbone model=GPT-4.1...Backbone model=GPT-4.1-mini, Optimizer=GPT-4.12026.02453MIPROv2Backbone model=GPT-4.1...Backbone model=GPT-4.1-mini, Optimizer=GPT-4.12026.022,275GEPABackbone model=GPT-4.1...Backbone model=GPT-4.1-mini, Optimizer=GPT-4.12026.022,320