ProgramBench Scores
Almost Resolved score: share of ProgramBench tasks passing at least 95% of hidden tests. Color = provider.
ProgramBench Scores
Almost Resolved score: share of ProgramBench tasks passing at least 95% of hidden tests. Color = provider.
ProgramBench Cost Efficiency
ProgramBench scores plotted against estimated effective cost per 1M I/O tokens (a runtime estimate, not a published task cost). Explicit reasoning/nonreasoning siblings are connected where both are public. Color = provider.
This chart is part of the ProgramBench benchmark page, which adds the model table, sources and how to read each view.
IQ DimensionsProgrammatic Reasoning IQ Bell CurveEach model's estimated Programmatic Reasoning IQ, placed on a standard normal IQ distribution.Data: Vals.ai, Full source leaderboard reconciliation, Full source leaderboard reconciliation +4 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 BenchmarksTerminal-Bench 4.0 ScoresExact AA v4.3.2 model/configuration; never substitute older benchmark versions. Contributes to Programmatic Reasoning using a provisional calibrated scale.Data: Artificial AnalysisOpen chartIQ BenchmarksLiveCodeBench Benchmark ScoresEach model's LiveCodeBench score. Color = provider.Data: Vals.ai, Full source leaderboard reconciliationOpen chartIQ BenchmarksIOI V2 Scores2024–2026 olympiad tasks, no interactive grading feedback. Version 2 only; separately calibrated from archived V1. Contributes to Programmatic Reasoning using a provisional calibrated scale.Data: Full source leaderboard reconciliationOpen chartIQ BenchmarksSWE-rebench Benchmark ScoresEach model's SWE-rebench resolved rate. Color = provider.Data: SWE-rebenchOpen chart