o3 Mini High (batch)
OpenAI · released Feb 12, 2025
OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...
Specification
- Context window
- 200K
- Max output
- 100K
- Knowledge cutoff
- Oct 31, 2023
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- Yes
Intelligence
15.7
51th percentile
Coding
16.3
Coding Index
Agentic
1.7
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 202586.0%
- MMLU-Pro80.2%
- GPQA Diamond77.3%
- LiveCodeBench73.4%
- IFBench67.1%
- AA-LCR (long context)42.0%
- SciCode39.8%
- τ²-bench (Telecom)31.3%
- Humanity's Last Exam12.0%
- Terminal-Bench Hard6.1%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| AIME 2025 | 86.0% |
| MMLU-Pro | 80.2% |
| GPQA Diamond | 77.3% |
| LiveCodeBench | 73.4% |
| IFBench | 67.1% |
| AA-LCR (long context) | 42.0% |
| SciCode | 39.8% |
| τ²-bench (Telecom) | 31.3% |
| Humanity's Last Exam | 12.0% |
| Terminal-Bench Hard | 6.1% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Gemini 2.5 ProGoogle16.1
- V3.2DeepSeek16.0
- o3 Mini High (batch)OpenAI15.7
- Gemini 3.1 Flash LiteGoogle15.6
- 15.6
- 15.6
- Claude Haiku 4.5Anthropic15.4
- Kimi K2 0905Moonshot AI15.3
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Gemini 2.5 Pro | 16.1 |
| V3.2 | 16.0 |
| o3 Mini High (batch) | 15.7 |
| Gemini 3.1 Flash Lite | 15.6 |
| Gemini 3.1 Flash Lite Preview | 15.6 |
| Qwen3.5-122B-A10B | 15.6 |
| Claude Haiku 4.5 | 15.4 |
| Kimi K2 0905 | 15.3 |
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
- $0.275
- 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.