GPT-5.5
OpenAI · released Apr 24, 2026
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
Specification
- Context window
- 1.05M
- Max output
- 128K
- Knowledge cutoff
- Dec 1, 2025
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 3
- Moderated
- Yes
- Uptime
- 99.9%
Intelligence
56.3
98th percentile
Coding
74.9
Coding Index
Agentic
47.4
Agentic Index
Output speed
85 t/s
Median across providers
Latency
2.19s
Time to first token
Cost per task
$2.65
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
- τ²-bench (Telecom)93.9%
- GPQA Diamond93.5%
- AA-LCR (long context)79.0%
- IFBench75.9%
- Terminal-Bench Hard60.6%
- SciCode56.1%
- Humanity's Last Exam45.8%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| τ²-bench (Telecom) | 93.9% |
| GPQA Diamond | 93.5% |
| AA-LCR (long context) | 79.0% |
| IFBench | 75.9% |
| Terminal-Bench Hard | 60.6% |
| SciCode | 56.1% |
| Humanity's Last Exam | 45.8% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Qwen3.8 MaxQwen58.1
- Claude Opus 4.8Anthropic57.3
- Muse Spark 1.2Meta56.8
- GPT-5.6 TerraOpenAI56.6
- GPT-5.5OpenAI56.3
- Grok 4.5xAI55.8
- Claude Sonnet 5Anthropic55.3
- Claude Opus 4.7Anthropic55.0
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Qwen3.8 Max | 58.1 |
| Claude Opus 4.8 | 57.3 |
| Muse Spark 1.2 | 56.8 |
| GPT-5.6 Terra | 56.6 |
| GPT-5.5 | 56.3 |
| Grok 4.5 | 55.8 |
| Claude Sonnet 5 | 55.3 |
| Claude Opus 4.7 | 55.0 |
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
- $5
- Output / 1M tokens
- $30
- Cached input / 1M
- $0.5
- Blended 3:1
- $11.25
One task, estimated
$2.65
- 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
- 1,336
- Win rate
- 60.7%
- Strongest at
- Game development
- Tournaments
- 3,578
Elo by category
Dot position on a 1,125–1,350 scale · Elo has no meaningful zero
- 1,336
- 1,292
- 1,283
- 1,280
- 1,278
- 1,250
- 1,209
- 1,128
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 | 1336 | 60.7% |
| UI components | 1292 | 56.3% |
| Data visualisation | 1283 | 56.6% |
| Websites | 1280 | 55.1% |
| SVG | 1278 | 58.1% |
| 3D scenes | 1250 | 52.0% |
| Mobile apps | 1209 | 51.7% |
| Full-stack apps | 1128 | 43.2% |