GPT-5.5 Instant
Made by OpenAI, released 5 May 2026. Epoch AI lists its access as “API access”. No Top tier or Strong results yet among the models listed here.
In short
What it does well
No Top tier or Strong ratings on the four main tests yet.
Where it falls short
- Coding: Behind the leaders (74th of 77 listed models)
- Maths: Behind the leaders (41st of 43 listed models)
- Writing: Middle (58th of 77 listed models)
What we don't know yet
- Web-building votes: Not enough data
- Short factual questions: Not enough data
- Fixing real software bugs: Not enough data
- Difficult coding tasks: 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
- MiddleHow often people preferred its answers to writing prompts. 1,418 on Arena's scale · Source for GPT-5.5 Instant writing score (lmarena)
- Coding
- Behind the leadersHow often people preferred its answers to coding questions. 1,433 on Arena's scale · Source for GPT-5.5 Instant coding score (lmarena)
- Maths
- Behind the leadersHow many very hard maths problems it solved. 26.3% · Source for GPT-5.5 Instant maths score (epoch)
- Knowledge
- Not enough dataNo result yet for short factual questions.
Evidence completeness: Partial evidence, 9 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
No category stands out as clearly stronger than its overall position.
Relatively weaker
No category stands out as clearly weaker than its overall position.
Show every category we can see
| Category | Position | Arena score | Votes | Source |
|---|---|---|---|---|
| Expert-level prompts Kind of request | 75th of 77 | 1,409 95% range 1,397 to 1,421 | 2,743 | Source for Expert-level prompts |
| Hard prompts Kind of request | 70th of 77 | 1,426 95% range 1,420 to 1,432 | 18,412 | Source for Hard prompts |
| Long prompts Kind of request | 69th of 77 | 1,422 95% range 1,415 to 1,429 | 12,541 | Source for Long prompts |
| Longer conversations Kind of request | 67th of 77 | 1,433 95% range 1,424 to 1,442 | 5,119 | Source for Longer conversations |
| Chinese Language | 70th of 76 | 1,456 95% range 1,441 to 1,471 | 1,715 | Source for Chinese |
| English prompts Language | 71st of 77 | 1,418 95% range 1,411 to 1,424 | 12,916 | Source for English prompts |
| French Language | 67th of 72 | 1,427 95% range 1,408 to 1,447 | 1,039 | Source for French |
| German Language | 51st of 55 | 1,411 95% range 1,382 to 1,439 | 431 | Source for German |
| Korean Language | 47th of 54 | 1,392 95% range 1,363 to 1,422 | 430 | Source for Korean |
| Non-English prompts Language | 70th of 77 | 1,417 95% range 1,411 to 1,423 | 14,212 | Source for Non-English prompts |
| Russian Language | 63rd of 77 | 1,430 95% range 1,419 to 1,442 | 3,024 | Source for Russian |
| Spanish Language | 61st of 70 | 1,430 95% range 1,408 to 1,451 | 813 | Source for Spanish |
| Entertainment, sport and media Topic | 62nd of 77 | 1,406 95% range 1,397 to 1,415 | 5,804 | Source for Entertainment, sport and media |
| Law and government Topic | 70th of 76 | 1,419 95% range 1,406 to 1,432 | 2,293 | Source for Law and government |
| Medicine and health Topic | 68th of 75 | 1,412 95% range 1,398 to 1,425 | 2,054 | Source for Medicine and health |
| Science Topic | 70th of 77 | 1,428 95% range 1,419 to 1,438 | 4,489 | Source for Science |
| Software and IT Topic | 72nd of 77 | 1,432 95% range 1,425 to 1,439 | 11,165 | 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
- Coding and building things: not ranked, because there is not enough data for the main test.
- Research and checking facts: not ranked, because there is not enough data for the main test.
Where an alternative might be more suitable
- Writing and creating content: rated Middle on writing votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Coding and building things: rated Behind the leaders on coding votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Homework and maths: rated Behind the leaders on hard maths problems. Compare it with GPT-6.1 Sol, the best-supported choice for this task.
- Business emails and everyday work: rated Behind the leaders on business-task votes. Compare it with Gemini 4 Argon, the best-supported choice for this task.
- Research and checking facts: no result on short factual questions, so we cannot say. See which models the evidence does support.
What it is
- Maker
- OpenAI
- Release date (Epoch AI)
- 5 May 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
Price not independently verified
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) |
1,419 Arena score 95% range 1,414 to 1,424, 27,128 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GPT-5.5 Instant lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.5 Instant Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,418 Arena score 95% range 1,408 to 1,427, 4,341 votes |
Middle | effort: not stated, bradley-terry rating | GPT-5.5 Instant lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.5 Instant Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,433 Arena score 95% range 1,426 to 1,441, 7,906 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GPT-5.5 Instant lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.5 Instant Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,420 Arena score 95% range 1,404 to 1,435, 1,530 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GPT-5.5 Instant lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.5 Instant Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,406 Arena score 95% range 1,399 to 1,413, 9,693 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GPT-5.5 Instant lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.5 Instant Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,410 Arena score 95% range 1,401 to 1,418, 5,673 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GPT-5.5 Instant lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.5 Instant 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 |
26.3% share of problems solved standard error ±2.6 points |
Behind the leaders | effort: not stated, best score across scorers | gpt-5.5-instant epoch · frontiermath_tiers_1_3_v2.csv |
2 Aug 2026 | Source for GPT-5.5 Instant 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 |
68.1% share of problems solved standard error ±6.2 points |
Behind the leaders | effort: not stated, best score across scorers | gpt-5.5-instant epoch · otis_mock_aime_2024_2025.csv |
2 Aug 2026 | Source for GPT-5.5 Instant OTIS Mock AIME 2024-2025 score (epoch) No public run log in the data file. |
| GPQA Diamond GPQA Diamond, benchmark released 2023-11-20 |
82.5% share of questions correct standard error ±2.3 points |
Behind the leaders | effort: not stated, best score across scorers | gpt-5.5-instant epoch · gpqa_diamond.csv |
2 Aug 2026 | Source for GPT-5.5 Instant GPQA Diamond score (epoch) No public run log in the data file. |
| SimpleQA Verified | Not enough data | |||||
| SWE-bench Verified (Epoch runs) | Not enough data | |||||
| FrontierCode (reported by Cognition) | Not enough data | |||||
Missing evidence
Not enough data for these tests:
- Arena WebDev: building web apps
- SimpleQA Verified
- SWE-bench Verified (Epoch runs)
- FrontierCode (reported by Cognition)
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.