GPT-5.6 Sol
OpenAI · released Jul 9, 2026
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...
Specification
- Context window
- 1.05M
- Max output
- 128K
- Knowledge cutoff
- Feb 16, 2026
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 3
- Moderated
- Yes
- Uptime
- 100.0%
Intelligence
60.9
99th percentile
Coding
77.4
Coding Index
Agentic
57.8
Agentic Index
Output speed
46 t/s
Median across providers
Latency
2.38s
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
- GPQA Diamond94.1%
- τ²-bench (Telecom)85.1%
- AA-LCR (long context)77.7%
- IFBench72.7%
- Terminal-Bench Hard65.9%
- SciCode56.1%
- Humanity's Last Exam49.5%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 94.1% |
| τ²-bench (Telecom) | 85.1% |
| AA-LCR (long context) | 77.7% |
| IFBench | 72.7% |
| Terminal-Bench Hard | 65.9% |
| SciCode | 56.1% |
| Humanity's Last Exam | 49.5% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Claude Opus 5Anthropic63.1
- Claude Fable 5Anthropic62.1
- GPT-5.6 SolOpenAI60.9
- Kimi K3Moonshot AI59.7
- Qwen3.8 MaxQwen58.1
- Claude Opus 4.8Anthropic57.3
- Muse Spark 1.2Meta56.8
- GPT-5.6 TerraOpenAI56.6
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Claude Opus 5 | 63.1 |
| Claude Fable 5 | 62.1 |
| GPT-5.6 Sol | 60.9 |
| Kimi K3 | 59.7 |
| Qwen3.8 Max | 58.1 |
| Claude Opus 4.8 | 57.3 |
| Muse Spark 1.2 | 56.8 |
| GPT-5.6 Terra | 56.6 |
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
- $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
- 1,380
- Win rate
- 62.7%
- Strongest at
- Game development
- Tournaments
- 1,265
Elo by category
Dot position on a 1,325–1,400 scale · Elo has no meaningful zero
- 1,380
- 1,365
- 1,365
- 1,364
- 1,344
- 1,343
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 | 1380 | 62.7% |
| UI components | 1365 | 59.6% |
| SVG | 1365 | 64.7% |
| 3D scenes | 1364 | 59.3% |
| Websites | 1344 | 59.8% |
| Data visualisation | 1343 | 57.9% |