GPT-5.5
Made by OpenAI, released 23 Apr 2026. Epoch AI lists its access as “API access”. Appears solid at coding, knowledge, maths and writing among the models listed here.
In short
What it does well
- Coding: Strong (28th of 77 listed models)
- Knowledge: Strong (12th of 43 listed models)
- Maths: Strong (12th of 43 listed models)
- Writing: Strong (25th of 77 listed models)
Where it falls short
The four main ratings show no weakness. That is not evidence it has none.
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
- StrongHow often people preferred its answers to writing prompts. 1,455 on Arena's scale · Source for GPT-5.5 writing score (lmarena)
- Coding
- StrongHow often people preferred its answers to coding questions. 1,494 on Arena's scale · Source for GPT-5.5 coding score (lmarena)
- Maths
- StrongHow many very hard maths problems it solved. 85.3% · Source for GPT-5.5 maths score (epoch)
- Knowledge
- StrongHow many short factual questions it answered correctly. 63.0% · Source for GPT-5.5 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
- Japanese: 7th of 54 on questions asked in Japanese, against 26th of 77 overall. Source for Japanese
- Korean: 7th of 54 on questions asked in Korean, against 26th of 77 overall. Source for Korean
Relatively weaker
- Medicine and health: 43rd of 75 on medicine and health questions, against 26th 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 | 18th of 77 | 1,507 95% range 1,500 to 1,515 | 7,403 | Source for Expert-level prompts |
| Hard prompts Kind of request | 19th of 77 | 1,489 95% range 1,485 to 1,493 | 45,556 | Source for Hard prompts |
| Long prompts Kind of request | 16th of 77 | 1,484 95% range 1,479 to 1,489 | 32,024 | Source for Long prompts |
| Longer conversations Kind of request | 24th of 77 | 1,476 95% range 1,469 to 1,483 | 11,829 | Source for Longer conversations |
| Chinese Language | 23rd of 76 | 1,525 95% range 1,516 to 1,535 | 4,490 | Source for Chinese |
| English prompts Language | 33rd of 77 | 1,470 95% range 1,466 to 1,475 | 31,558 | Source for English prompts |
| French Language | 29th of 72 | 1,482 95% range 1,469 to 1,496 | 2,507 | Source for French |
| German Language | 29th of 55 | 1,459 95% range 1,440 to 1,478 | 1,053 | Source for German |
| Japanese Language | 7th of 54 | 1,499 95% range 1,478 to 1,520 | 910 | Source for Japanese |
| Korean Language | 7th of 54 | 1,460 95% range 1,442 to 1,478 | 1,184 | Source for Korean |
| Non-English prompts Language | 21st of 77 | 1,467 95% range 1,463 to 1,472 | 37,818 | Source for Non-English prompts |
| Russian Language | 25th of 77 | 1,473 95% range 1,465 to 1,480 | 7,340 | Source for Russian |
| Spanish Language | 26th of 70 | 1,469 95% range 1,455 to 1,483 | 1,943 | Source for Spanish |
| Entertainment, sport and media Topic | 22nd of 77 | 1,449 95% range 1,443 to 1,455 | 16,712 | Source for Entertainment, sport and media |
| Law and government Topic | 16th of 76 | 1,491 95% range 1,483 to 1,500 | 5,622 | Source for Law and government |
| Medicine and health Topic | 43rd of 75 | 1,457 95% range 1,448 to 1,466 | 5,242 | Source for Medicine and health |
| Science Topic | 23rd of 77 | 1,485 95% range 1,479 to 1,492 | 11,623 | Source for Science |
| Software and IT Topic | 25th of 77 | 1,493 95% range 1,488 to 1,498 | 27,468 | 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 Strong 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.
- Homework and maths: rated Strong on hard maths problems. Compare it with GPT-6.1 Sol, the best-supported choice for this task.
- Research and checking facts: rated Strong 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)
- 23 Apr 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) |
1,472 Arena score 95% range 1,468 to 1,475, 69,377 votes |
Strong | effort: High, bradley-terry rating | GPT-5.5 (High) lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.5 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,455 Arena score 95% range 1,449 to 1,462, 13,129 votes |
Strong | effort: High, bradley-terry rating | GPT-5.5 (High) lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.5 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,494 Arena score 95% range 1,489 to 1,500, 19,166 votes |
Strong | effort: High, bradley-terry rating | GPT-5.5 (High) lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.5 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,478 Arena score 95% range 1,468 to 1,489, 3,474 votes |
Strong | effort: High, bradley-terry rating | GPT-5.5 (High) lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.5 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,479 Arena score 95% range 1,473 to 1,484, 24,014 votes |
Top tier | effort: High, bradley-terry rating | GPT-5.5 (High) lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.5 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,478 Arena score 95% range 1,472 to 1,484, 13,727 votes |
Top tier | effort: High, bradley-terry rating | GPT-5.5 (High) lmarena · text/latest |
28 Oct 2026 | Source for GPT-5.5 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 |
85.3% share of problems solved standard error ±2.1 points |
Strong | effort: xhigh, best score across scorers | gpt-5.5_xhigh epoch · frontiermath_tiers_1_3_v2.csv |
11 Jun 2026 | Source for GPT-5.5 FrontierMath Tiers 1-3 (v2) score (epoch) No public run log in the data file. |
| OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025, benchmark released 2024-12-19 |
84.4% share of problems solved standard error ±5.5 points |
Behind the leaders | effort: low, best score across scorers | gpt-5.5_low epoch · otis_mock_aime_2024_2025.csv |
7 Aug 2026 | Source for GPT-5.5 OTIS Mock AIME 2024-2025 score (epoch) · Run details for OTIS Mock AIME 2024-2025 |
| GPQA Diamond GPQA Diamond, benchmark released 2023-11-20 |
90.7% share of questions correct standard error ±1.8 points |
Middle | effort: low, best score across scorers | gpt-5.5_low epoch · gpqa_diamond.csv |
5 May 2026 | Source for GPT-5.5 GPQA Diamond score (epoch) · Run details for GPQA Diamond |
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
63.0% share of questions correct standard error ±1.5 points |
Strong | effort: xhigh, best score across scorers | gpt-5.5_xhigh epoch · simpleqa_verified.csv |
27 Aug 2026 | Source for GPT-5.5 SimpleQA Verified score (epoch) · Run details for SimpleQA Verified |
| SWE-bench Verified (Epoch runs) | Not enough data | |||||
| FrontierCode (reported by Cognition) FrontierCode, benchmark released 2026-06-08, aggregation Mean@5 |
43.0% mean score over 5 attempts no uncertainty figure published |
Not rated (results use different tools) | effort: xhigh, tool: codex, mean@5 | gpt-5.5_unknown epoch · frontiercode_external.csv |
not provided | Source for GPT-5.5 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.