OpenAI
o3-pro
o3-pro is one of OpenAI's reasoning-focused models, built for harder multi-step tasks where deliberate problem solving matters more than simple chat completion. The benchmark snapshot highlights how that reasoning emphasis translates into scores, latency, and value versus general-purpose models.
Introducing o3 and o4-miniOperational Metrics
Output Speed16.9 tok/s
First Token98.15s
Blended Price$35.00/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseJun 10, 2025
Context Windown/a
Modalitiesn/a
Strength: GPQA
Rank #58 across 478 models.
84.5%
Strength: Overall
Rank #71 across 500 models.
40.7
Watch Area: Output $
Rank #323 across 325 models.
$80.00/M
Watch Area: Blended $
Rank #322 across 325 models.
$35.00/M
Watch Area: Input $
Rank #322 across 325 models.
$20.00/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.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 40.7 | #71 |
| GPQA | reasoning | 84.5% | #58 |
| Output Speed | speed | 16.9 tok/s | #290 |
| Time to First Token | speed | 98.15s | #289 |
| Blended Price |