Programmatic Reasoning IQ Over Time
Each model's estimated Programmatic Reasoning IQ by release date. Step-lines connect each provider's flagship models over time.
Programmatic Reasoning IQ Over Time
CoreIQ Bell CurveEach model's estimated IQ, placed on a standard normal IQ distribution.Data: ARC Prize, Full source leaderboard reconciliation, Full source leaderboard reconciliation +27 moreOpen chartIQ BenchmarksTerminal-Bench 4.0 ScoresExact AA v5.0.1 model/configuration for Terminal-Bench 4.0; retained historical observations keep original provenance. Existing IQ calibration is unchanged. 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 BenchmarksProgramBench ScoresAlmost Resolved score: share of ProgramBench tasks passing at least 95% of hidden tests. Color = provider.Data: 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