evals.report
BenchmarksLabsCompareRun guides
OpenAIOpenAI o-series (o3)

OpenAI o3-pro

OpenAI · OpenAI o-series (o3). Released Jun 10, 2025.

7 results

Benchmark results 7

Compare this model
BenchmarkCategoryScoreMetricStatusDate
GPQA DiamondReasoning84%accuracyUnverifiedJun 10, 2025Details
Artificial Analysis Intelligence IndexReasoning40.7IndexUnverifiedJun 10, 2025Details
Epoch Capabilities IndexReasoning148.1IndexOfficialJun 10, 2025Details
Aider PolyglotCoding84.9%% correctOfficialJun 10, 2025Details
MultiChallengeReasoning62.40%accuracyVerifiedJun 10, 2025Details
MASK (Model Alignment between Statements and Knowledge)Other82.50Honesty scoreVerifiedJun 10, 2025Details
Vectara Hallucination LeaderboardOther23.3%Hallucination RateOfficialJun 10, 2025Details