o4 Mini (batch)
OpenAI · released Apr 16, 2025
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...
Specification
- Context window
- 200K
- Max output
- 100K
- Knowledge cutoff
- Jun 30, 2024
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- Yes
Intelligence
26.1
69th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
—
Median across providers
Latency
—
Time to first token
Cost per task
$0.20
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- AIME 202590.7%
- LiveCodeBench85.9%
- MMLU-Pro83.2%
- GPQA Diamond78.4%
- IFBench68.7%
- AA-LCR (long context)60.0%
- τ²-bench (Telecom)55.6%
- SciCode46.5%
- Humanity's Last Exam16.5%
- Terminal-Bench Hard15.2%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| AIME 2025 | 90.7% |
| LiveCodeBench | 85.9% |
| MMLU-Pro | 83.2% |
| GPQA Diamond | 78.4% |
| IFBench | 68.7% |
| AA-LCR (long context) | 60.0% |
| τ²-bench (Telecom) | 55.6% |
| SciCode | 46.5% |
| Humanity's Last Exam | 16.5% |
| Terminal-Bench Hard | 15.2% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Step 3.5 FlashStepFun26.5
- o4 Mini (batch)OpenAI26.1
- o4 Mini HighOpenAI26.1
- o4 MiniOpenAI26.1
- Claude Opus 4Anthropic26.0
- Claude Sonnet 4Anthropic26.0
- Gemini 2.5 ProGoogle25.9
- GPT-5 MiniOpenAI25.8
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Step 3.5 Flash | 26.5 |
| o4 Mini (batch) | 26.1 |
| o4 Mini High | 26.1 |
| o4 Mini | 26.1 |
| Claude Opus 4 | 26.0 |
| Claude Sonnet 4 | 26.0 |
| Gemini 2.5 Pro | 25.9 |
| GPT-5 Mini | 25.8 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.55
- Output / 1M tokens
- $2.2
- Cached input / 1M
- $0.138
- Blended 3:1
- $0.963
One task, estimated
$0.20
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.