GLM-5.2
Made by Z.ai (Zhipu AI), released 16 Jun 2026. Epoch AI lists its access as “Open weights (unrestricted)”. Appears strongest at writing among the models listed here.
In short
What it does well
- Writing: Top tier (20th of 77 listed models)
- Coding: Strong (35th of 77 listed models)
Where it falls short
- Knowledge: Behind the leaders (36th of 43 listed models)
- Maths: Middle (29th of 43 listed models)
What we don't know yet
Every test we use has a result.
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
- Top tierHow often people preferred its answers to writing prompts. 1,461 on Arena's scale · Source for GLM-5.2 writing score (lmarena)
- Coding
- StrongHow often people preferred its answers to coding questions. 1,487 on Arena's scale · Source for GLM-5.2 coding score (lmarena)
- Maths
- MiddleHow many very hard maths problems it solved. 59.2% · Source for GLM-5.2 maths score (epoch)
- Knowledge
- Behind the leadersHow many short factual questions it answered correctly. 34.2% · Source for GLM-5.2 knowledge score (epoch)
Evidence completeness: Broad evidence, 13 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 | 36th of 77 | 1,488 95% range 1,480 to 1,497 | 5,595 | Source for Expert-level prompts |
| Hard prompts Kind of request | 33rd of 77 | 1,481 95% range 1,476 to 1,485 | 34,803 | Source for Hard prompts |
| Long prompts Kind of request | 25th of 77 | 1,479 95% range 1,474 to 1,484 | 24,397 | Source for Long prompts |
| Longer conversations Kind of request | 32nd of 77 | 1,469 95% range 1,462 to 1,476 | 8,490 | Source for Longer conversations |
| Chinese Language | 24th of 76 | 1,523 95% range 1,513 to 1,533 | 3,876 | Source for Chinese |
| English prompts Language | 30th of 77 | 1,475 95% range 1,470 to 1,480 | 21,897 | Source for English prompts |
| French Language | 34th of 72 | 1,476 95% range 1,461 to 1,491 | 2,010 | Source for French |
| German Language | 21st of 55 | 1,471 95% range 1,452 to 1,491 | 966 | Source for German |
| Japanese Language | 22nd of 54 | 1,450 95% range 1,428 to 1,472 | 887 | Source for Japanese |
| Korean Language | 20th of 54 | 1,438 95% range 1,419 to 1,457 | 1,037 | Source for Korean |
| Non-English prompts Language | 28th of 77 | 1,458 95% range 1,454 to 1,463 | 31,793 | Source for Non-English prompts |
| Russian Language | 31st of 77 | 1,467 95% range 1,459 to 1,475 | 6,377 | Source for Russian |
| Spanish Language | 15th of 70 | 1,478 95% range 1,462 to 1,493 | 1,651 | Source for Spanish |
| Entertainment, sport and media Topic | 25th of 77 | 1,448 95% range 1,442 to 1,454 | 13,277 | Source for Entertainment, sport and media |
| Law and government Topic | 17th of 76 | 1,487 95% range 1,478 to 1,497 | 4,327 | Source for Law and government |
| Medicine and health Topic | 28th of 75 | 1,475 95% range 1,465 to 1,485 | 3,933 | Source for Medicine and health |
| Science Topic | 21st of 77 | 1,488 95% range 1,481 to 1,495 | 8,917 | Source for Science |
| Software and IT Topic | 33rd of 77 | 1,487 95% range 1,481 to 1,492 | 20,769 | 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
- 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 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 Strong on business-task votes. Compare it with Gemini 4 Argon, the best-supported choice for this task.
- Research and checking facts: rated Behind the leaders 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)
- 16 Jun 2026
- Access, as listed by Epoch AI
- Open weights (unrestricted)
- 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
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 (unrestricted)”. 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) |
1,470 Arena score 95% range 1,466 to 1,474, 53,702 votes |
Strong | effort: Max, bradley-terry rating | GLM-5.2 (Max) lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.2 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,461 Arena score 95% range 1,454 to 1,468, 10,646 votes |
Top tier | effort: Max, bradley-terry rating | GLM-5.2 (Max) lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.2 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,487 Arena score 95% range 1,481 to 1,493, 14,324 votes |
Strong | effort: Max, bradley-terry rating | GLM-5.2 (Max) lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.2 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,484 Arena score 95% range 1,472 to 1,496, 2,423 votes |
Strong | effort: Max, bradley-terry rating | GLM-5.2 (Max) lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.2 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,466 Arena score 95% range 1,460 to 1,471, 18,494 votes |
Strong | effort: Max, bradley-terry rating | GLM-5.2 (Max) lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.2 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,451 Arena score 95% range 1,444 to 1,457, 10,212 votes |
Strong | effort: Max, bradley-terry rating | GLM-5.2 (Max) lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.2 Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,606 Arena score 95% range 1,600 to 1,612, 17,817 votes |
Strong | effort: Max, bradley-terry rating | GLM-5.2 (Max) lmarena · webdev/latest |
28 Oct 2026 | Source for GLM-5.2 Arena WebDev: building web apps score (lmarena) |
| FrontierMath Tiers 1-3 (v2) FrontierMath Tiers 1-3 v2 (private set), benchmark released 2026-06-12 |
59.2% share of problems solved standard error ±3.0 points |
Middle | effort: max, best score across scorers | glm-5.2_max epoch · frontiermath_tiers_1_3_v2.csv |
19 Jun 2026 | Source for GLM-5.2 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 |
86.4% share of problems solved standard error ±4.2 points |
Behind the leaders | effort: max, best score across scorers | glm-5.2_max epoch · otis_mock_aime_2024_2025.csv |
25 Jun 2026 | Source for GLM-5.2 OTIS Mock AIME 2024-2025 score (epoch) No public run log in the data file. |
| GPQA Diamond GPQA Diamond, benchmark released 2023-11-20 |
91.9% share of questions correct standard error ±1.6 points |
Strong | effort: max, best score across scorers | glm-5.2_max epoch · gpqa_diamond.csv |
24 Jun 2026 | Source for GLM-5.2 GPQA Diamond score (epoch) No public run log in the data file. |
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
34.2% share of questions correct standard error ±1.5 points |
Behind the leaders | effort: max, best score across scorers | glm-5.2_max epoch · simpleqa_verified.csv |
27 Aug 2026 | Source for GLM-5.2 SimpleQA Verified score (epoch) · Run details for SimpleQA Verified |
| SWE-bench Verified (Epoch runs) SWE-bench Verified, benchmark released 2024-08-13, as run by Epoch AI |
78.7% share of issues resolved standard error ±1.9 points |
Top tier | effort: max, best score across scorers | glm-5.2_max epoch · swe_bench_verified.csv |
25 Jun 2026 | Source for GLM-5.2 SWE-bench Verified (Epoch runs) score (epoch) · Run details for SWE-bench Verified (Epoch runs) |
| FrontierCode (reported by Cognition) FrontierCode, benchmark released 2026-06-08, aggregation Mean@5 |
24.5% mean score over 5 attempts no uncertainty figure published |
Not rated (results use different tools) | effort: none, tool: mini-swe-agent, mean@5 | glm-5.2_none epoch · frontiercode_external.csv |
not provided | Source for GLM-5.2 FrontierCode (reported by Cognition) score (epoch) · Run details for FrontierCode (reported by Cognition) |
Missing evidence
Every test we use has a result for this 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.