o3-mini

OpenAI · openai/o3-mini

ProviderOpenAI
Familyo-mini
Typellm-reasoning
Statusactive
Released2024-12-20
Updated2025-01-29

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.
BenchmarkCatalogue standingScore
Aider Polyglot Benchmarkunassessed80.5
AIME 2025unassessed83.3
Arena Elo — Codingunassessed1350.0
Arena Elo — Hard Promptsunassessed1401.1
Arena Elo — Mathunassessed1370.0
Arena Elo — Overall (Text)unassessed1340.0
Arena Elo — Style Controlunassessed1363.2
GPQA Diamondunassessed79.7
HumanEvalunassessed88.9
IFEvalunassessed86.5
LiveCodeBenchunassessed71.7
MATH-500unassessed94.8
MedQAunassessed91.4
MGSM (Multilingual Grade School Math)unassessed92.0
MMLU-Prounassessed79.0
MultiPL-E: C#unassessed82.5
MultiPL-E: Juliaunassessed64.2
MultiPL-E: Kotlin (unconfirmed)unassessed75.2
MultiPL-E: Luaunassessed58.5
MultiPL-E: Perlunassessed54.2
MultiPL-E: PHPunassessed80.2
MultiPL-E: Runassessed60.5
MultiPL-E: Rubyunassessed68.5
MultiPL-E: Scalaunassessed63.2
MultiPL-E: Swiftunassessed68.2
SWE-bench Agentunassessed62.8
SWE-bench Verifiedunassessed71.2
τ-benchunassessed65.5
Terminal-Benchunassessed58.2

Data

This card as JSON · Edit on GitHub