GPT-5.6 Terra
Made by OpenAI, released 9 Jul 2026. Epoch AI lists its access as “API access”. Appears strongest at maths among the models listed here.
In short
What it does well
- Maths: Top tier (9th of 43 listed models)
- Coding: Strong (39th of 77 listed models)
Where it falls short
- Writing: Behind the leaders (61st of 77 listed models)
- Knowledge: Middle (30th of 43 listed models)
What we don't know yet
- Web-building votes: Not enough data
- Fixing real software bugs: Not enough data
The four ratings
- Top tier
- Strong
- Middle
- Behind the leaders
- Not enough data
Ratings compare only the 77 models listed here, in quarters, best first. “Not enough data” means no result yet. It is never a low score.
- Writing
- Behind the leadersHow often people preferred its answers to writing prompts. 1,413 on Arena's scale · Source for GPT-5.6 Terra writing score (lmarena)
- Coding
- StrongHow often people preferred its answers to coding questions. 1,485 on Arena's scale · Source for GPT-5.6 Terra coding score (lmarena)
- Maths
- Top tierHow many very hard maths problems it solved. 86.0% · Source for GPT-5.6 Terra maths score (epoch)
- Knowledge
- MiddleHow many short factual questions it answered correctly. 43.2% · Source for GPT-5.6 Terra knowledge score (epoch)
Evidence completeness: Broad evidence, 11 of 13 tests have a result.
Where it is relatively stronger or weaker
This compares each kind of request with the model's own overall position among the 77 listed models, using Arena's votes. It is about performance on different languages, kinds of request and topics, not about political or social bias.
Relatively stronger
- Expert-level prompts: 28th of 77 on prompts that need expert knowledge, against 47th of 77 overall. Source for Expert-level prompts
- Chinese: 30th of 76 on questions asked in Chinese, against 47th of 77 overall. Source for Chinese
Relatively weaker
- Medicine and health: 61st of 75 on medicine and health questions, against 47th of 77 overall. Source for Medicine and health
Show every category we can see
| Category | Position | Arena score | Votes | Source |
|---|---|---|---|---|
| Expert-level prompts Kind of request | 28th of 77 | 1,495 95% range 1,487 to 1,504 | 5,537 | Source for Expert-level prompts |
| Hard prompts Kind of request | 40th of 77 | 1,469 95% range 1,464 to 1,474 | 31,313 | Source for Hard prompts |
| Long prompts Kind of request | 48th of 77 | 1,453 95% range 1,447 to 1,458 | 22,238 | Source for Long prompts |
| Longer conversations Kind of request | 44th of 77 | 1,455 95% range 1,447 to 1,462 | 7,713 | Source for Longer conversations |
| Chinese Language | 30th of 76 | 1,514 95% range 1,503 to 1,524 | 3,821 | Source for Chinese |
| English prompts Language | 61st of 77 | 1,449 95% range 1,443 to 1,454 | 19,456 | Source for English prompts |
| French Language | 44th of 72 | 1,468 95% range 1,452 to 1,484 | 1,576 | Source for French |
| German Language | 28th of 55 | 1,460 95% range 1,439 to 1,482 | 777 | Source for German |
| Japanese Language | 26th of 54 | 1,445 95% range 1,422 to 1,468 | 810 | Source for Japanese |
| Korean Language | 27th of 54 | 1,426 95% range 1,405 to 1,447 | 903 | Source for Korean |
| Non-English prompts Language | 41st of 77 | 1,441 95% range 1,436 to 1,446 | 28,700 | Source for Non-English prompts |
| Russian Language | 42nd of 77 | 1,453 95% range 1,445 to 1,462 | 5,582 | Source for Russian |
| Spanish Language | 45th of 70 | 1,448 95% range 1,433 to 1,464 | 1,488 | Source for Spanish |
| Entertainment, sport and media Topic | 53rd of 77 | 1,419 95% range 1,412 to 1,426 | 12,344 | Source for Entertainment, sport and media |
| Law and government Topic | 42nd of 76 | 1,461 95% range 1,451 to 1,471 | 4,041 | Source for Law and government |
| Medicine and health Topic | 61st of 75 | 1,432 95% range 1,421 to 1,443 | 3,432 | Source for Medicine and health |
| Science Topic | 58th of 77 | 1,453 95% range 1,446 to 1,461 | 7,835 | Source for Science |
| Software and IT Topic | 40th of 77 | 1,482 95% range 1,476 to 1,487 | 18,481 | Source for Software and IT |
Bias: what we can and can't see
Our sources do not measure political lean, stereotyping, flattery (agreeing with you too readily) or safety behaviour, so we cannot say how any model does on those. What we can show is above: where a model is relatively stronger or weaker across languages, kinds of request and topics. Also, people voting in Arena can favour answer style, such as length and formatting, and our numbers do not adjust for that. See what AI bias means and what these tests can tell you.
Best-supported use cases
This model is not among the options we recommend for any of the five tasks. That reflects the rules and the models listed, not a verdict on the model.
Where an alternative might be more suitable
- Writing and creating content: rated Behind the leaders on writing votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Coding and building things: rated Strong on coding votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Business emails and everyday work: rated Middle on business-task votes. Compare it with Gemini 4 Argon, the best-supported choice for this task.
- Research and checking facts: rated Middle on short factual questions. Compare it with Gemini 4 Argon, the best-supported choice for this task.
What it is
- Maker
- OpenAI
- Release date (Epoch AI)
- 9 Jul 2026
- Access, as listed by Epoch AI
- API access
- Licence, as listed by Arena
- Proprietary
- Maker's country (Epoch AI)
- United States of America
- Last observation in our data
- 28 Oct 2026
- Data last changed
- 29 Oct 2026, 14:36 UTC
We have not verified an official product page for this model, so we do not link to one.
How you can use it
Proprietary. The model's files are not published, so it is generally available only through its maker or partners the maker chooses.
How you can reach it (an app, a website, a developer API or a third-party tool) and what that costs are not covered by our benchmark data. Where we could verify prices from the maker's own pages, they are shown under Price. Epoch AI lists access as “API access”. See models, apps and harnesses and how AI pricing works.
Price
Verified consumer plans that include this model
- ChatGPT Plus: GBP 20.00 per month. Maker's page, checked 29 Oct 2026. Comparison table cell for this model on this plan: "Yes". The page says limits apply.
- ChatGPT Pro (from): GBP 89.00 per month. Maker's page, checked 29 Oct 2026. Comparison table cell for this model on this plan: "Unlimited*". Listed as 'From £89 / month' with a choice of 3 usage tiers.
Prices change and can differ by country. Check the maker's page before you pay.
See ChatGPT plans and pricing (checked 29 Oct 2026). Page opened and read in the browser. Which plan includes which model comes from its comparison table.
We never infer subscription prices from API prices. New to “tokens” and “per million”? See how AI pricing works.
Good to remember
- Benchmarks are samples of tasks. None proves performance in every situation.
- Arena scores come from people choosing between answers. That measures preference, not correctness.
- Ratings are relative to the 77 models listed here. A different set would change them.
- Sources test models at different settings. Each result shows the setting used, and we do not adjust it.
The evidence, for the curious
Show all 13 tests with settings and sources
| Test | Result | Rating | Setting used | Source identifier | Observed | Links |
|---|---|---|---|---|---|---|
| Arena text: overall preference Arena 'text' leaderboard (Bradley-Terry rating, no style control) |
1,448 Arena score 95% range 1,444 to 1,452, 48,166 votes |
Middle | effort: xHigh, bradley-terry rating | GPT-5.6 Terra (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.6 Terra Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,413 Arena score 95% range 1,406 to 1,420, 10,250 votes |
Behind the leaders | effort: xHigh, bradley-terry rating | GPT-5.6 Terra (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.6 Terra Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,485 Arena score 95% range 1,479 to 1,492, 12,713 votes |
Strong | effort: xHigh, bradley-terry rating | GPT-5.6 Terra (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.6 Terra Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,464 Arena score 95% range 1,451 to 1,476, 2,205 votes |
Middle | effort: xHigh, bradley-terry rating | GPT-5.6 Terra (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.6 Terra Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,455 Arena score 95% range 1,449 to 1,460, 17,170 votes |
Strong | effort: xHigh, bradley-terry rating | GPT-5.6 Terra (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.6 Terra Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,447 Arena score 95% range 1,440 to 1,454, 8,881 votes |
Middle | effort: xHigh, bradley-terry rating | GPT-5.6 Terra (xHigh) lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.6 Terra Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps | Not enough data | |||||
| FrontierMath Tiers 1-3 (v2) FrontierMath Tiers 1-3 v2 (private set), benchmark released 2026-06-12 |
86.0% share of problems solved standard error ±2.1 points |
Top tier | effort: max, best score across scorers | gpt-5.6-terra_max epoch · frontiermath_tiers_1_3_v2.csv |
9 Jul 2026 | Source for GPT-5.6 Terra FrontierMath Tiers 1-3 (v2) score (epoch) · Run details for FrontierMath Tiers 1-3 (v2) |
| OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025, benchmark released 2024-12-19 |
99.7% share of problems solved standard error ±0.3 points |
Top tier | effort: max, best score across scorers | gpt-5.6-terra_max epoch · otis_mock_aime_2024_2025.csv |
9 Jul 2026 | Source for GPT-5.6 Terra OTIS Mock AIME 2024-2025 score (epoch) No public run log in the data file. |
| GPQA Diamond GPQA Diamond, benchmark released 2023-11-20 |
93.3% share of questions correct standard error ±1.5 points |
Top tier | effort: max, best score across scorers | gpt-5.6-terra_max epoch · gpqa_diamond.csv |
9 Jul 2026 | Source for GPT-5.6 Terra GPQA Diamond score (epoch) No public run log in the data file. |
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
43.2% share of questions correct standard error ±1.6 points |
Middle | effort: max, best score across scorers | gpt-5.6-terra_max epoch · simpleqa_verified.csv |
10 Aug 2026 | Source for GPT-5.6 Terra SimpleQA Verified score (epoch) No public run log in the data file. |
| SWE-bench Verified (Epoch runs) | Not enough data | |||||
| FrontierCode (reported by Cognition) FrontierCode, benchmark released 2026-06-08, aggregation Mean@5 |
41.3% mean score over 5 attempts no uncertainty figure published |
Not rated (results use different tools) | effort: max, tool: codex, mean@5 | gpt-5.6-terra_unknown epoch · frontiercode_external.csv |
not provided | Source for GPT-5.6 Terra FrontierCode (reported by Cognition) score (epoch) · Run details for FrontierCode (reported by Cognition) |
Missing evidence
Not enough data for these tests:
- Arena WebDev: building web apps
- SWE-bench Verified (Epoch runs)
Missing results are not low scores and do not count against the model.
Where a source gives no public run log, we cannot show the run behind the score. See data sources.
Not sure this is the right one?
Tell us what you need help with and we'll narrow the options down.