GPT-5.1
OpenAI · released Nov 13, 2025
GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...
Specification
- Context window
- 400K
- Max output
- 128K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 2
- Moderated
- Yes
- Uptime
- 100.0%
Intelligence
37.5
85th percentile
Coding
49.4
Coding Index
Agentic
21.6
Agentic Index
Output speed
47 t/s
Median across providers
Latency
542ms
Time to first token
Cost per task
$0.86
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 202594.0%
- GPQA Diamond87.3%
- MMLU-Pro87.0%
- LiveCodeBench86.8%
- τ²-bench (Telecom)81.9%
- AA-LCR (long context)76.7%
- IFBench72.9%
- Terminal-Bench Hard45.5%
- SciCode43.3%
- Humanity's Last Exam28.5%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| AIME 2025 | 94.0% |
| GPQA Diamond | 87.3% |
| MMLU-Pro | 87.0% |
| LiveCodeBench | 86.8% |
| τ²-bench (Telecom) | 81.9% |
| AA-LCR (long context) | 76.7% |
| IFBench | 72.9% |
| Terminal-Bench Hard | 45.5% |
| SciCode | 43.3% |
| Humanity's Last Exam | 28.5% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- MiMo-V2.5Xiaomi38.0
- Grok 4.20xAI38.0
- Grok 4.3xAI37.9
- Ling-3.0-flashInclusionAI37.8
- Qwen3.6 27BQwen37.7
- GPT-5.1OpenAI37.5
- Gemini 3.5 Flash LiteGoogle37.4
- Claude Sonnet 4.6Anthropic36.8
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| MiMo-V2.5 | 38.0 |
| Grok 4.20 | 38.0 |
| Grok 4.3 | 37.9 |
| Ling-3.0-flash | 37.8 |
| Qwen3.6 27B | 37.7 |
| GPT-5.1 | 37.5 |
| Gemini 3.5 Flash Lite | 37.4 |
| Claude Sonnet 4.6 | 36.8 |
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
- $1.25
- Output / 1M tokens
- $10
- Cached input / 1M
- $0.125
- Blended 3:1
- $3.44
One task, estimated
$0.86
- 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).
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
- 1,232
- Win rate
- 58.0%
- Strongest at
- Data visualisation
- Tournaments
- 464
Elo by category
Dot position on a 1,100–1,250 scale · Elo has no meaningful zero
- 1,232
- 1,220
- 1,210
- 1,202
- 1,196
- 1,117
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| Data visualisation | 1232 | 58.0% |
| Game development | 1220 | 56.0% |
| Websites | 1210 | 54.1% |
| UI components | 1202 | 53.0% |
| SVG | 1196 | 57.4% |
| 3D scenes | 1117 | 43.9% |