OpenAI
o3-mini
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...
Introducing o3 and o4-miniModel Snapshot
ReleaseJan 31, 2025
Context200,000
Overall
Rank #236 across 566
19.0
Coding
No rank
n/a
Blended Price
Rank #234 across 371
$1.93/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed210.5 tok/s
First Token5.36s
Max Output100,000
Pricing
Blended$1.93/M
Input$1.10/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 19.0 | #236 |
| MMLU-Pro | reasoning | 79.1% | #135 |
| GPQA | reasoning | 74.8% | #209 |
| Humanity's Last Exam | reasoning | 8.7% | #225 |
| LiveCodeBench |