List your company

Web Browsing on BrowseComp+ (test)

56.4AccuracyACE + Optimizer State
27.835.22542.6550.075Apr 3, 2026

Evaluation results

MethodLinks
ACE + Optimizer StateAgent Model=GPT-5.4 Nano, Optimizer Model=Claude Opus, Optimization Iterations=302026.0456.4
ACE + Auxiliary LossesAgent Model=GPT-5.4 Nano, Optimizer Model=Claude Opus, Optimization Iterations=302026.0454.7
RCL (all primitives)Agent Model=GPT-5.4 Nano, Optimizer Model=Claude Opus, Optimization Iterations=302026.0451.3
ACE + Grouped RolloutsAgent Model=GPT-5.4 Nano, Optimizer Model=Claude Opus, Optimization Iterations=302026.0450.7
ACEAgent Model=GPT-5.4 Nano, Optimizer Model=Claude Opus, Optimization Iterations=302026.0450
GEPAAgent Model=GPT-5.4 Nano, Optimizer Model=Claude Opus, Optimization Iterations=302026.0448.7
ACE + BatchingAgent Model=GPT-5.4 Nano, Optimizer Model=Claude Opus, Optimization Iterations=302026.0448.3
ACE + Failure ReplayAgent Model=GPT-5.4 Nano, Optimizer Model=Claude Opus, Optimization Iterations=302026.0447.3
ACE + Credit AssignmentAgent Model=GPT-5.4 Nano, Optimizer Model=Claude Opus, Optimization Iterations=302026.0446.3
SeedAgent Model=GPT-5.4 Nano, Optimizer Model=Claude Opus, Optimization Iterations=302026.0440.7
ACE + Failure ReplayAgent Model=Gemini 3.1 Flash Lite, Optimizer Model=Claude Opus, Optimization Iterations=302026.0440
ACE + Grouped RolloutsAgent Model=Gemini 3.1 Flash Lite, Optimizer Model=Claude Opus, Optimization Iterations=302026.0438.7
ACE + Auxiliary LossesAgent Model=Gemini 3.1 Flash Lite, Optimizer Model=Claude Opus, Optimization Iterations=302026.0438
ACEAgent Model=Gemini 3.1 Flash Lite, Optimizer Model=Claude Opus, Optimization Iterations=302026.0437.3
ACE + Credit AssignmentAgent Model=Gemini 3.1 Flash Lite, Optimizer Model=Claude Opus, Optimization Iterations=302026.0437.3
RCL (all primitives)Agent Model=Gemini 3.1 Flash Lite, Optimizer Model=Claude Opus, Optimization Iterations=302026.0437.3
ACE + Optimizer StateAgent Model=Gemini 3.1 Flash Lite, Optimizer Model=Claude Opus, Optimization Iterations=302026.0436
GEPAAgent Model=Gemini 3.1 Flash Lite, Optimizer Model=Claude Opus, Optimization Iterations=302026.0435.3
ACE + BatchingAgent Model=Gemini 3.1 Flash Lite, Optimizer Model=Claude Opus, Optimization Iterations=302026.0431.3
SeedAgent Model=Gemini 3.1 Flash Lite, Optimizer Model=Claude Opus, Optimization Iterations=302026.0428.9