GLM-5.3
Made by Z.ai (Zhipu AI), released 14 Aug 2026. Epoch AI lists its access as “Open weights (restricted use)”. Appears solid at coding, maths and writing among the models listed here.
In short
What it does well
- Coding: Strong (24th of 77 listed models)
- Maths: Strong (22nd of 43 listed models)
- Writing: Strong (21st of 77 listed models)
Where it falls short
- Knowledge: 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. 1,459 on Arena's scale · Source for GLM-5.3 writing score (lmarena)
- Coding
- StrongHow often people preferred its answers to coding questions. 1,497 on Arena's scale · Source for GLM-5.3 coding score (lmarena)
- Maths
- StrongHow many very hard maths problems it solved. 68.8% · Source for GLM-5.3 maths score (epoch)
- Knowledge
- MiddleHow many short factual questions it answered correctly. 41.0% · Source for GLM-5.3 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 | 12th of 77 | 1,517 95% range 1,505 to 1,529 | 2,588 | Source for Expert-level prompts |
| Hard prompts Kind of request | 18th of 77 | 1,490 95% range 1,484 to 1,496 | 16,697 | Source for Hard prompts |
| Long prompts Kind of request | 19th of 77 | 1,483 95% range 1,477 to 1,490 | 11,977 | Source for Long prompts |
| Longer conversations Kind of request | 31st of 77 | 1,470 95% range 1,460 to 1,480 | 3,952 | Source for Longer conversations |
| Chinese Language | 12th of 76 | 1,532 95% range 1,518 to 1,545 | 2,058 | Source for Chinese |
| English prompts Language | 16th of 77 | 1,483 95% range 1,476 to 1,489 | 10,670 | Source for English prompts |
| French Language | 14th of 72 | 1,496 95% range 1,475 to 1,516 | 920 | Source for French |
| German Language | 11th of 55 | 1,491 95% range 1,463 to 1,520 | 413 | Source for German |
| Japanese Language | 20th of 54 | 1,458 95% range 1,430 to 1,486 | 489 | Source for Japanese |
| Korean Language | 10th of 54 | 1,457 95% range 1,429 to 1,485 | 458 | Source for Korean |
| Non-English prompts Language | 27th of 77 | 1,460 95% range 1,454 to 1,465 | 15,931 | Source for Non-English prompts |
| Russian Language | 28th of 77 | 1,471 95% range 1,460 to 1,481 | 3,432 | Source for Russian |
| Spanish Language | 29th of 70 | 1,466 95% range 1,446 to 1,486 | 856 | Source for Spanish |
| Entertainment, sport and media Topic | 26th of 77 | 1,448 95% range 1,440 to 1,456 | 7,008 | Source for Entertainment, sport and media |
| Law and government Topic | 33rd of 76 | 1,473 95% range 1,460 to 1,486 | 2,277 | Source for Law and government |
| Medicine and health Topic | 20th of 75 | 1,483 95% range 1,469 to 1,497 | 1,957 | Source for Medicine and health |
| Science Topic | 16th of 77 | 1,498 95% range 1,489 to 1,507 | 4,477 | Source for Science |
| Software and IT Topic | 24th of 77 | 1,494 95% range 1,487 to 1,500 | 9,675 | 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.
- Business emails and everyday work: rated Strong 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
- Z.ai (Zhipu AI)
- Release date (Epoch AI)
- 14 Aug 2026
- Access, as listed by Epoch AI
- Open weights (restricted use)
- Licence, as listed by Arena
- MIT
- Maker's country (Epoch AI)
- China
- Last observation in our data
- 28 Oct 2026
- Data last changed
- 29 Oct 2026, 14:36 UTC
'GLM-5.3-Flash' is a different model and is not merged with this one.
We have not verified an official product page for this model, so we do not link to one.
How you can use it
Open weights. Arena lists its licence as MIT. In plain terms, the model's files are published under a licence that lets others run it, so it can be offered by more than one company, sometimes at lower cost. That does not guarantee that any particular app is free. Open licences differ, and some restrict commercial use, so check the licence terms before building a business on it.
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 “Open weights (restricted use)”. See models, apps and harnesses and how AI pricing works.
Price
Price not independently verified
See GLM Coding Plan (checked 28 Oct 2026). Page opened and read. It names GLM models but states no prices or which plan includes which.
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) |
1,474 Arena score 95% range 1,469 to 1,479, 26,606 votes |
Strong | effort: Max, bradley-terry rating | GLM-5.3 (Max) lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.3 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,459 Arena score 95% range 1,451 to 1,468, 6,017 votes |
Strong | effort: Max, bradley-terry rating | GLM-5.3 (Max) lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.3 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,497 Arena score 95% range 1,489 to 1,505, 6,323 votes |
Strong | effort: Max, bradley-terry rating | GLM-5.3 (Max) lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.3 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,497 Arena score 95% range 1,480 to 1,514, 1,158 votes |
Top tier | effort: Max, bradley-terry rating | GLM-5.3 (Max) lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.3 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,481 Arena score 95% range 1,474 to 1,488, 8,831 votes |
Top tier | effort: Max, bradley-terry rating | GLM-5.3 (Max) lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.3 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,461 Arena score 95% range 1,452 to 1,470, 4,834 votes |
Strong | effort: Max, bradley-terry rating | GLM-5.3 (Max) lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.3 Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,623 Arena score 95% range 1,616 to 1,630, 11,150 votes |
Strong | effort: Max, bradley-terry rating | GLM-5.3 (Max) lmarena · webdev/latest |
28 Oct 2026 | Source for GLM-5.3 Arena WebDev: building web apps score (lmarena) |
| FrontierMath Tiers 1-3 (v2) FrontierMath Tiers 1-3 v2 (private set), benchmark released 2026-06-12 |
68.8% share of problems solved standard error ±2.7 points |
Strong | effort: max, best score across scorers | glm-5.3_max epoch · frontiermath_tiers_1_3_v2.csv |
25 Aug 2026 | Source for GLM-5.3 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 |
91.1% share of problems solved standard error ±3.5 points |
Middle | effort: max, best score across scorers | glm-5.3_max epoch · otis_mock_aime_2024_2025.csv |
24 Aug 2026 | Source for GLM-5.3 OTIS Mock AIME 2024-2025 score (epoch) No public run log in the data file. |
| GPQA Diamond GPQA Diamond, benchmark released 2023-11-20 |
90.9% share of questions correct standard error ±1.6 points |
Strong | effort: max, best score across scorers | glm-5.3_max epoch · gpqa_diamond.csv |
24 Aug 2026 | Source for GLM-5.3 GPQA Diamond score (epoch) No public run log in the data file. |
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
41.0% share of questions correct standard error ±1.6 points |
Middle | effort: max, best score across scorers | glm-5.3_max epoch · simpleqa_verified.csv |
28 Aug 2026 | Source for GLM-5.3 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 |
40.1% mean score over 5 attempts no uncertainty figure published |
Not rated (results use different tools) | effort: max, tool: devin-cli, mean@5 | glm-5.3_max epoch · frontiercode_external.csv |
not provided | Source for GLM-5.3 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.