GPT-5 Mini
OpenAI · released Aug 7, 2025
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....
Specification
- Context window
- 400K
- Max output
- 128K
- Knowledge cutoff
- May 31, 2024
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 2
- Moderated
- Yes
- Uptime
- 100.0%
Intelligence
16.8
61th percentile
Coding
15.6
Coding Index
Agentic
6.8
Agentic Index
Output speed
119 t/s
Median across providers
Latency
2.76s
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 202590.7%
- LiveCodeBench83.8%
- MMLU-Pro83.7%
- GPQA Diamond82.8%
- IFBench75.4%
- AA-LCR (long context)72.3%
- τ²-bench (Telecom)68.4%
- SciCode39.0%
- Terminal-Bench Hard33.3%
- Humanity's Last Exam21.5%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| AIME 2025 | 90.7% |
| LiveCodeBench | 83.8% |
| MMLU-Pro | 83.7% |
| GPQA Diamond | 82.8% |
| IFBench | 75.4% |
| AA-LCR (long context) | 72.3% |
| τ²-bench (Telecom) | 68.4% |
| SciCode | 39.0% |
| Terminal-Bench Hard | 33.3% |
| Humanity's Last Exam | 21.5% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- GPT-5 MiniOpenAI16.8
- o4 Mini HighOpenAI16.7
- o4 MiniOpenAI16.7
- Step 3.5 FlashStepFun16.6
- Claude Sonnet 4Anthropic16.6
- Gemini 2.5 ProGoogle16.1
- V3.2DeepSeek16.0
- Gemini 3.1 Flash LiteGoogle15.6
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| GPT-5 Mini | 16.8 |
| o4 Mini High | 16.7 |
| o4 Mini | 16.7 |
| Step 3.5 Flash | 16.6 |
| Claude Sonnet 4 | 16.6 |
| Gemini 2.5 Pro | 16.1 |
| V3.2 | 16.0 |
| Gemini 3.1 Flash Lite | 15.6 |
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
- $0.025
- 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).
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
- 1,132
- Win rate
- 46.5%
- Strongest at
- Game development
- Tournaments
- 5,244
Elo by category
Dot position on a 1,025–1,150 scale · Elo has no meaningful zero
- 1,132
- 1,131
- 1,127
- 1,107
- 1,089
- 1,038
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 | 1132 | 46.5% |
| Data visualisation | 1131 | 43.7% |
| Websites | 1127 | 44.3% |
| UI components | 1107 | 41.9% |
| SVG | 1089 | 45.8% |
| 3D scenes | 1038 | 36.9% |