GPT-5.6 Terra
OpenAI · released Jul 9, 2026
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...
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
56.6
98th percentile
Coding
76.7
Coding Index
Agentic
50.2
Agentic Index
Output speed
56 t/s
Median across providers
Latency
1.5s
Time to first token
Cost per task
$0.53
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 Diamond92.5%
- τ²-bench (Telecom)86.3%
- AA-LCR (long context)79.7%
- IFBench71.2%
- Terminal-Bench Hard57.6%
- SciCode53.9%
- Humanity's Last Exam42.9%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 92.5% |
| τ²-bench (Telecom) | 86.3% |
| AA-LCR (long context) | 79.7% |
| IFBench | 71.2% |
| Terminal-Bench Hard | 57.6% |
| SciCode | 53.9% |
| Humanity's Last Exam | 42.9% |
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
- $1
- Output / 1M tokens
- $6
- Cached input / 1M
- $0.1
- Blended 3:1
- $2.25
One task, estimated
$0.53
- 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
- 1,297
- Win rate
- 53.0%
- Strongest at
- UI components
- Tournaments
- 1,103
Elo by category
Dot position on a 1,075–1,300 scale · Elo has no meaningful zero
- 1,297
- 1,296
- 1,277
- 1,255
- 1,254
- 1,195
- 1,165
- 1,095
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 | 1297 | 53.0% |
| Websites | 1296 | 53.9% |
| Game development | 1277 | 51.0% |
| Data visualisation | 1255 | 50.2% |
| SVG | 1254 | 51.8% |
| 3D scenes | 1195 | 40.0% |
| Mobile apps | 1165 | 42.6% |
| Full-stack apps | 1095 | 31.9% |