GPT-5.4 (batch)
OpenAI · released Mar 5, 2026
GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...
Specification
- Context window
- 1.05M
- Max output
- 128K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- Yes
Intelligence
53.1
97th percentile
Coding
71.1
Coding Index
Agentic
44.2
Agentic Index
Output speed
—
Median across providers
Latency
—
Time to first token
Cost per task
$0.66
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
- GPQA Diamond92.0%
- τ²-bench (Telecom)87.1%
- AA-LCR (long context)77.7%
- IFBench73.9%
- Terminal-Bench Hard57.6%
- SciCode56.6%
- Humanity's Last Exam43.7%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 92.0% |
| τ²-bench (Telecom) | 87.1% |
| AA-LCR (long context) | 77.7% |
| IFBench | 73.9% |
| Terminal-Bench Hard | 57.6% |
| SciCode | 56.6% |
| Humanity's Last Exam | 43.7% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Muse Spark 1.1Meta53.2
- GPT-5.4 (batch)OpenAI53.1
- GPT-5.4OpenAI53.1
- GLM 5.2Z.ai52.6
- GPT-5.6 LunaOpenAI52.3
- Gemini 3.5 FlashGoogle52.0
- V4 Flash 0731DeepSeek51.8
- V4 Flash 0423DeepSeek51.8
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Muse Spark 1.1 | 53.2 |
| GPT-5.4 (batch) | 53.1 |
| GPT-5.4 | 53.1 |
| GLM 5.2 | 52.6 |
| GPT-5.6 Luna | 52.3 |
| Gemini 3.5 Flash | 52.0 |
| V4 Flash 0731 | 51.8 |
| V4 Flash 0423 | 51.8 |
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
- $7.5
- Cached input / 1M
- $0.125
- Blended 3:1
- $2.81
One task, estimated
$0.66
- 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
- 1,250
- Win rate
- 63.6%
- Strongest at
- UI components
- Tournaments
- 129
Elo by category
Dot position on a 1,050–1,250 scale · Elo has no meaningful zero
- 1,250
- 1,236
- 1,223
- 1,221
- 1,188
- 1,120
- 1,147
- 1,059
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| UI components | 1250 | 63.6% |
| Game development | 1236 | 53.6% |
| Data visualisation | 1223 | 52.2% |
| Websites | 1221 | 50.8% |
| SVG | 1188 | 53.2% |
| 3D scenes | 1120 | 39.0% |
| Mobile apps | 1147 | 45.9% |
| Full-stack apps | 1059 | 40.8% |