evals.report
BenchmarksLabsCompareRun guides
OpenAIo-series

o4-mini

OpenAI · o-series. Released Apr 16, 2025.

2 results

Benchmark results 2

Compare this model
BenchmarkCategoryScoreMetricStatusDate
FrontierMathReasoning24.83%accuracyOfficialMay 30, 2026Details
Berkeley Function Calling LeaderboardTool use53.24%accuracyOfficialApr 12, 2026Details