GPT-5 (batch)
OpenAI · released Aug 7, 2025
GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...
Specification
- Context window
- 400K
- Max output
- 128K
- Knowledge cutoff
- Sep 30, 2024
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- Yes
Intelligence
35.3
82th percentile
Coding
37.8
Coding Index
Agentic
26.5
Agentic Index
Output speed
—
Median across providers
Latency
—
Time to first token
Cost per task
$0.43
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 202594.3%
- MMLU-Pro87.1%
- GPQA Diamond85.4%
- τ²-bench (Telecom)84.8%
- LiveCodeBench84.6%
- AA-LCR (long context)76.3%
- IFBench73.1%
- SciCode42.9%
- Terminal-Bench Hard32.6%
- 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 | 94.3% |
| MMLU-Pro | 87.1% |
| GPQA Diamond | 85.4% |
| τ²-bench (Telecom) | 84.8% |
| LiveCodeBench | 84.6% |
| AA-LCR (long context) | 76.3% |
| IFBench | 73.1% |
| SciCode | 42.9% |
| Terminal-Bench Hard | 32.6% |
| Humanity's Last Exam | 28.5% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- V4 Pro 0813DeepSeek36.0
- V4 Pro 0423DeepSeek36.0
- GPT-5 (batch)OpenAI35.3
- V4 Flash 0731DeepSeek34.3
- V4 Flash 0423DeepSeek34.3
- Gemini 3.6 FlashGoogle34.0
- KAT-Coder-Pro V2KwaiPilot33.9
- Qwen3.8 27BQwen33.7
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| V4 Pro 0813 | 36.0 |
| V4 Pro 0423 | 36.0 |
| GPT-5 (batch) | 35.3 |
| V4 Flash 0731 | 34.3 |
| V4 Flash 0423 | 34.3 |
| Gemini 3.6 Flash | 34.0 |
| KAT-Coder-Pro V2 | 33.9 |
| Qwen3.8 27B | 33.7 |
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
- $0.625
- Output / 1M tokens
- $5
- Cached input / 1M
- $0.063
- Blended 3:1
- $1.72
One task, estimated
$0.43
- 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
- 1,262
- Win rate
- 62.9%
- Strongest at
- Data visualisation
- Tournaments
- 232
Elo by category
Dot position on a 1,100–1,275 scale · Elo has no meaningful zero
- 1,262
- 1,235
- 1,227
- 1,217
- 1,207
- 1,111
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 | 1262 | 62.9% |
| SVG | 1235 | 64.1% |
| Game development | 1227 | 59.5% |
| UI components | 1217 | 58.2% |
| Websites | 1207 | 53.8% |
| 3D scenes | 1111 | 41.4% |