GPT-5.1-Codex-Mini
OpenAI · released Nov 13, 2025
GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex
Specification
- Context window
- 400K
- Max output
- 128K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- No
- Uptime
- 100.0%
Intelligence
31.3
76th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
65 t/s
Median across providers
Latency
3.58s
Time to first token
Cost per task
$0.17
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 202591.7%
- LiveCodeBench83.6%
- MMLU-Pro82.0%
- GPQA Diamond81.3%
- IFBench67.9%
- AA-LCR (long context)65.0%
- τ²-bench (Telecom)62.9%
- SciCode42.6%
- Terminal-Bench Hard33.3%
- Humanity's Last Exam18.5%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| AIME 2025 | 91.7% |
| LiveCodeBench | 83.6% |
| MMLU-Pro | 82.0% |
| GPQA Diamond | 81.3% |
| IFBench | 67.9% |
| AA-LCR (long context) | 65.0% |
| τ²-bench (Telecom) | 62.9% |
| SciCode | 42.6% |
| Terminal-Bench Hard | 33.3% |
| Humanity's Last Exam | 18.5% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- 32.5
- Qwen3.6 35B A3BQwen32.1
- M2.1MiniMax32.1
- GPT-5.1-Codex-MiniOpenAI31.3
- 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 Max Thinking | 32.5 |
| Qwen3.6 35B A3B | 32.1 |
| M2.1 | 32.1 |
| GPT-5.1-Codex-Mini | 31.3 |
| 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
- $0.25
- Output / 1M tokens
- $2
- Cached input / 1M
- $0.03
- Blended 3:1
- $0.688
One task, estimated
$0.17
- 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.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,134
- Win rate
- 43.4%
- Strongest at
- Game development
- Tournaments
- 4,183
Elo by category
Dot position on a 1,025–1,150 scale · Elo has no meaningful zero
- 1,134
- 1,133
- 1,124
- 1,115
- 1,043
- 1,025
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| Game development | 1134 | 43.4% |
| Websites | 1133 | 42.8% |
| Data visualisation | 1124 | 40.7% |
| UI components | 1115 | 41.0% |
| 3D scenes | 1043 | 32.8% |
| SVG | 1025 | 35.3% |