o3-mini
ActiveCost-efficient reasoning model with strong STEM performance.
Overview
o3-mini is OpenAI's small reasoning model offering strong performance on math and coding benchmarks at significantly lower cost than o3 or o1.
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| AIME 2024Math | 63.3% accuracy | Self-reported OpenAI system card |
| GSM8KMath | 97% accuracy | Self-reported OpenAI system card |
| HumanEvalCoding | 93.5pass@1 % | Self-reported OpenAI system card |
| MATHMath | 90% accuracy | Self-reported OpenAI system card |
| SWE-bench VerifiedCoding | 49.3% resolved | Self-reported OpenAI system card |
Integrations & tooling support
- Tool calling
- Supported
- Structured outputs
- Supported
Price vs quality
Fair value
Mid-tier performance and pricing — standard choice.
- Quality percentile
- 56.9%
- Effective price
- $3.575/1M
- Pricing breakdown
- $1.1/1M in
$4.4/1M out
vs 5 benchmarks
/ 1M tokens (input + 3× output)
Community ratings
No ratings yet. Be the first to rate o3-mini.
Rate o3-mini
Sign in to rate and review.
Comments
Sign in to leave a comment.