GPT-5 Mini (batch)
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
- 1
- Moderated
- Yes
Intelligence
25.8
68th percentile
Coding
15.6
Coding Index
Agentic
19.6
Agentic Index
Output speed
—
Median across providers
Latency
—
Time to first token
Cost per task
$0.09
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)71.0%
- τ²-bench (Telecom)68.4%
- SciCode39.2%
- 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) | 71.0% |
| τ²-bench (Telecom) | 68.4% |
| SciCode | 39.2% |
| Terminal-Bench Hard | 33.3% |
| Humanity's Last Exam | 21.5% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- o4 Mini HighOpenAI26.1
- Claude Opus 4Anthropic26.0
- Claude Sonnet 4Anthropic26.0
- Gemini 2.5 ProGoogle25.9
- GPT-5 Mini (batch)OpenAI25.8
- GPT-5 MiniOpenAI25.8
- Gemini 3.1 Flash LiteGoogle25.6
- 25.6
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| o4 Mini High | 26.1 |
| Claude Opus 4 | 26.0 |
| Claude Sonnet 4 | 26.0 |
| Gemini 2.5 Pro | 25.9 |
| GPT-5 Mini (batch) | 25.8 |
| GPT-5 Mini | 25.8 |
| Gemini 3.1 Flash Lite | 25.6 |
| Gemini 3.1 Flash Lite Preview | 25.6 |
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
- $0.125
- Output / 1M tokens
- $1
- Cached input / 1M
- $0.013
- Blended 3:1
- $0.344
One task, estimated
$0.09
- 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
- 1,171
- Win rate
- 46.5%
- Strongest at
- Game development
- Tournaments
- 5,228
Elo by category
Dot position on a 1,075–1,175 scale · Elo has no meaningful zero
- 1,171
- 1,157
- 1,147
- 1,141
- 1,138
- 1,092
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 | 1171 | 46.5% |
| Data visualisation | 1157 | 43.6% |
| Websites | 1147 | 44.3% |
| UI components | 1141 | 41.9% |
| SVG | 1138 | 45.8% |
| 3D scenes | 1092 | 36.9% |