Arena.ai Agent Arena Scores
Aggregate net improvement across real-world Agent Mode sessions. Color = provider.
Arena.ai Agent Arena Scores
Aggregate net improvement across real-world Agent Mode sessions. Color = provider.
Agent Arena Cost Efficiency
Source-matched Agent Arena Net Improvement and median session-cost configurations from the methodology window. Each line is one canonical model. Color = provider.
This chart is part of the Agent Arena benchmark page, which adds the model table, sources and how to read each view.
IQ DimensionsComputer Use IQ Bell CurveEach model's estimated Computer Use IQ, placed on a standard normal IQ distribution.Data: LLM Stats, Full source leaderboard reconciliation, OSWorld +5 moreOpen chartCoreIQ Bell CurveEach model's estimated IQ, placed on a standard normal IQ distribution.Data: ARC Prize, Full source leaderboard reconciliation, Full source leaderboard reconciliation +26 moreOpen chartIQ BenchmarksBrowseComp Benchmark ScoresEach model's BrowseComp score. Color = provider.Data: LLM Stats, Full source leaderboard reconciliationOpen chartIQ BenchmarksMCP Atlas Benchmark ScoresReal-world MCP tool-use pass rates. Color = provider.Data: Scale Labs, Full source leaderboard reconciliationOpen chartIQ BenchmarksAgents' Last Exam Benchmark ScoresFull / Overall pass rates from Agents' Last Exam. Color = provider.Data: Agents' Last ExamOpen chartIQ BenchmarksOSWorld-Verified Benchmark ScoresEach model's OSWorld-Verified score. Color = provider.Data: LLM Stats, OSWorld, Full source leaderboard reconciliationOpen chart