OpenAI
o4-mini (high)
o4-mini (high) 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 Speed124.5 tok/s
First Token17.05s
Blended Price$1.93/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseApr 16, 2025
Context Windown/a
Modalitiesn/a
Strength: AIME
Rank #3 across 194 models.
94.0%
Strength: MATH-500
Rank #7 across 201 models.
98.9%
Strength: LCB
Rank #12 across 343 models.
85.9%
Watch Area: TTFT
Rank #268 across 293 models.
17.05s
Watch Area: Input $
Rank #223 across 325 models.
$1.10/M
Watch Area: Blended $
Rank #221 across 325 models.
$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.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 33.1 | #118 |
| Artificial Analysis Coding Index | coding | 25.6 | #144 |
| Artificial Analysis Math Index | math | 90.7 | #24 |
| MMLU-Pro | reasoning | 83.2% | #58 |