o3 (batch)
OpenAI · released Apr 16, 2025
o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....
Specification
- Context window
- 200K
- Max output
- 100K
- Knowledge cutoff
- Jun 30, 2024
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- Yes
Intelligence
31.1
75th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
104 t/s
Median across providers
Latency
6.98s
Time to first token
Cost per task
$0.37
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 202588.3%
- MMLU-Pro85.3%
- GPQA Diamond82.7%
- LiveCodeBench80.8%
- τ²-bench (Telecom)80.7%
- AA-LCR (long context)73.3%
- IFBench71.4%
- SciCode41.0%
- Terminal-Bench Hard37.1%
- Humanity's Last Exam20.1%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| AIME 2025 | 88.3% |
| MMLU-Pro | 85.3% |
| GPQA Diamond | 82.7% |
| LiveCodeBench | 80.8% |
| τ²-bench (Telecom) | 80.7% |
| AA-LCR (long context) | 73.3% |
| IFBench | 71.4% |
| SciCode | 41.0% |
| Terminal-Bench Hard | 37.1% |
| Humanity's Last Exam | 20.1% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Qwen3.6 35B A3BQwen32.1
- M2.1MiniMax32.1
- GPT-5.1-Codex-MiniOpenAI31.3
- o3 (batch)OpenAI31.1
- Ring-2.6-1TInclusionAI31.1
- o3OpenAI31.1
- Step 3.7 FlashStepFun30.9
- Mistral Medium 3.5Mistral AI30.4
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Qwen3.6 35B A3B | 32.1 |
| M2.1 | 32.1 |
| GPT-5.1-Codex-Mini | 31.3 |
| o3 (batch) | 31.1 |
| Ring-2.6-1T | 31.1 |
| o3 | 31.1 |
| Step 3.7 Flash | 30.9 |
| Mistral Medium 3.5 | 30.4 |
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
- $1
- Output / 1M tokens
- $4
- Cached input / 1M
- $0.25
- Blended 3:1
- $1.75
One task, estimated
$0.37
- 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.