Grok 4.5
Made by xAI, released 8 Jul 2026. Epoch AI lists its access as “API access”. Appears solid at writing among the models listed here.
In short
What it does well
- Writing: Strong (33rd of 77 listed models)
Where it falls short
- Coding: Middle (46th of 77 listed models)
- Knowledge: Middle (24th of 43 listed models)
- Maths: Middle (32nd of 43 listed models)
What we don't know yet
- 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. 1,442 on Arena's scale · Source for Grok 4.5 writing score (lmarena)
- Coding
- MiddleHow often people preferred its answers to coding questions. 1,474 on Arena's scale · Source for Grok 4.5 coding score (lmarena)
- Maths
- MiddleHow many very hard maths problems it solved. 57.2% · Source for Grok 4.5 maths score (epoch)
- Knowledge
- MiddleHow many short factual questions it answered correctly. 48.3% · Source for Grok 4.5 knowledge score (epoch)
Evidence completeness: Broad evidence, 12 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 | 52nd of 77 | 1,465 95% range 1,455 to 1,474 | 4,708 | Source for Expert-level prompts |
| Hard prompts Kind of request | 45th of 77 | 1,462 95% range 1,457 to 1,467 | 26,590 | Source for Hard prompts |
| Long prompts Kind of request | 38th of 77 | 1,462 95% range 1,456 to 1,468 | 19,221 | Source for Long prompts |
| Longer conversations Kind of request | 42nd of 77 | 1,456 95% range 1,448 to 1,464 | 6,634 | Source for Longer conversations |
| Chinese Language | 46th of 76 | 1,494 95% range 1,483 to 1,506 | 3,036 | Source for Chinese |
| English prompts Language | 53rd of 77 | 1,453 95% range 1,447 to 1,458 | 16,168 | Source for English prompts |
| French Language | 52nd of 72 | 1,457 95% range 1,439 to 1,475 | 1,283 | Source for French |
| German Language | 41st of 55 | 1,446 95% range 1,423 to 1,469 | 684 | Source for German |
| Japanese Language | 30th of 54 | 1,429 95% range 1,402 to 1,456 | 544 | Source for Japanese |
| Korean Language | 45th of 54 | 1,403 95% range 1,380 to 1,425 | 739 | Source for Korean |
| Non-English prompts Language | 45th of 77 | 1,440 95% range 1,435 to 1,445 | 23,631 | Source for Non-English prompts |
| Russian Language | 44th of 77 | 1,450 95% range 1,441 to 1,459 | 4,584 | Source for Russian |
| Spanish Language | 43rd of 70 | 1,451 95% range 1,432 to 1,469 | 1,077 | Source for Spanish |
| Entertainment, sport and media Topic | 39th of 77 | 1,433 95% range 1,426 to 1,440 | 10,323 | Source for Entertainment, sport and media |
| Law and government Topic | 40th of 76 | 1,463 95% range 1,452 to 1,474 | 3,322 | Source for Law and government |
| Medicine and health Topic | 59th of 75 | 1,440 95% range 1,428 to 1,452 | 2,923 | Source for Medicine and health |
| Science Topic | 41st of 77 | 1,465 95% range 1,457 to 1,472 | 6,520 | Source for Science |
| Software and IT Topic | 47th of 77 | 1,471 95% range 1,465 to 1,477 | 15,970 | 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 Middle on coding votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Homework and maths: rated Middle on hard maths problems. Compare it with GPT-6.1 Sol, 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
- xAI
- Release date (Epoch AI)
- 8 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
Price not independently verified
See Grok (checked 29 Oct 2026). Page opened and read. It says Grok is 'free to try on the web and in the apps' and that SuperGrok adds higher limits. It states no prices or model names. The separate plans page opens as a sign-up pop-up showing introductory offers and no model names, so we record nothing else.
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 1,443 to 1,452, 39,801 votes |
Middle | effort: not stated, bradley-terry rating | Grok 4.5 lmarena · text/latest |
28 Oct 2026 | Source for Grok 4.5 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,442 Arena score 95% range 1,434 to 1,450, 8,215 votes |
Strong | effort: not stated, bradley-terry rating | Grok 4.5 lmarena · text/latest |
28 Oct 2026 | Source for Grok 4.5 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,474 Arena score 95% range 1,467 to 1,481, 11,123 votes |
Middle | effort: not stated, bradley-terry rating | Grok 4.5 lmarena · text/latest |
28 Oct 2026 | Source for Grok 4.5 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,459 Arena score 95% range 1,445 to 1,473, 1,756 votes |
Middle | effort: not stated, bradley-terry rating | Grok 4.5 lmarena · text/latest |
28 Oct 2026 | Source for Grok 4.5 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,445 Arena score 95% range 1,439 to 1,451, 14,483 votes |
Middle | effort: not stated, bradley-terry rating | Grok 4.5 lmarena · text/latest |
28 Oct 2026 | Source for Grok 4.5 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,441 Arena score 95% range 1,434 to 1,449, 7,618 votes |
Middle | effort: not stated, bradley-terry rating | Grok 4.5 lmarena · text/latest |
28 Oct 2026 | Source for Grok 4.5 Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,553 Arena score 95% range 1,546 to 1,560, 11,018 votes |
Strong | effort: not stated, bradley-terry rating | Grok 4.5 lmarena · webdev/latest |
28 Oct 2026 | Source for Grok 4.5 Arena WebDev: building web apps score (lmarena) |
| FrontierMath Tiers 1-3 (v2) FrontierMath Tiers 1-3 v2 (private set), benchmark released 2026-06-12 |
57.2% share of problems solved standard error ±2.9 points |
Middle | effort: high, best score across scorers | grok-4.5_high epoch · frontiermath_tiers_1_3_v2.csv |
9 Jul 2026 | Source for Grok 4.5 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 |
97.8% share of problems solved standard error ±1.3 points |
Strong | effort: high, best score across scorers | grok-4.5_high epoch · otis_mock_aime_2024_2025.csv |
8 Jul 2026 | Source for Grok 4.5 OTIS Mock AIME 2024-2025 score (epoch) No public run log in the data file. |
| GPQA Diamond GPQA Diamond, benchmark released 2023-11-20 |
93.4% share of questions correct standard error ±1.4 points |
Top tier | effort: high, best score across scorers | grok-4.5_high epoch · gpqa_diamond.csv |
8 Jul 2026 | Source for Grok 4.5 GPQA Diamond score (epoch) No public run log in the data file. |
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
48.3% share of questions correct standard error ±1.6 points |
Middle | effort: high, best score across scorers | grok-4.5_high epoch · simpleqa_verified.csv |
27 Aug 2026 | Source for Grok 4.5 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 |
42.4% mean score over 5 attempts no uncertainty figure published |
Not rated (results use different tools) | effort: high, tool: grok-build, mean@5 | grok-4.5_unknown epoch · frontiercode_external.csv |
not provided | Source for Grok 4.5 FrontierCode (reported by Cognition) score (epoch) · Run details for FrontierCode (reported by Cognition) |
Missing evidence
Not enough data for these tests:
- 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.