GLM-5
Made by Z.ai (Zhipu AI), released 11 Feb 2026. Epoch AI lists its access as “Open weights (unrestricted)”. 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: Middle (58th of 77 listed models)
- Writing: Middle (41st of 77 listed models)
What we don't know yet
- Hard maths problems: Not enough data
- Short factual questions: 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. 1,438 on Arena's scale · Source for GLM-5 writing score (lmarena)
- Coding
- MiddleHow often people preferred its answers to coding questions. 1,461 on Arena's scale · Source for GLM-5 coding score (lmarena)
- Maths
- Not enough dataNo result yet for hard maths problems.
- Knowledge
- Not enough dataNo result yet for short factual questions.
Evidence completeness: Broad evidence, 10 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
- Chinese: 31st of 76 on questions asked in Chinese, against 52nd of 77 overall. Source for Chinese
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 | 60th of 77 | 1,454 95% range 1,442 to 1,465 | 2,610 | Source for Expert-level prompts |
| Hard prompts Kind of request | 58th of 77 | 1,452 95% range 1,446 to 1,457 | 18,200 | Source for Hard prompts |
| Long prompts Kind of request | 55th of 77 | 1,446 95% range 1,439 to 1,452 | 11,117 | Source for Long prompts |
| Longer conversations Kind of request | 41st of 77 | 1,456 95% range 1,447 to 1,465 | 4,683 | Source for Longer conversations |
| Chinese Language | 31st of 76 | 1,511 95% range 1,498 to 1,524 | 2,019 | Source for Chinese |
| English prompts Language | 46th of 77 | 1,457 95% range 1,452 to 1,463 | 12,908 | Source for English prompts |
| French Language | 54th of 72 | 1,456 95% range 1,436 to 1,476 | 910 | Source for French |
| German Language | 40th of 55 | 1,446 95% range 1,420 to 1,472 | 510 | Source for German |
| Korean Language | 32nd of 54 | 1,422 95% range 1,397 to 1,447 | 555 | Source for Korean |
| Non-English prompts Language | 61st of 77 | 1,430 95% range 1,425 to 1,435 | 16,347 | Source for Non-English prompts |
| Russian Language | 58th of 77 | 1,436 95% range 1,426 to 1,446 | 3,448 | Source for Russian |
| Spanish Language | 40th of 70 | 1,453 95% range 1,435 to 1,471 | 1,130 | Source for Spanish |
| Entertainment, sport and media Topic | 47th of 77 | 1,425 95% range 1,417 to 1,433 | 5,901 | Source for Entertainment, sport and media |
| Law and government Topic | 49th of 76 | 1,454 95% range 1,441 to 1,466 | 2,273 | Source for Law and government |
| Medicine and health Topic | 47th of 75 | 1,455 95% range 1,442 to 1,468 | 2,136 | Source for Medicine and health |
| Science Topic | 47th of 77 | 1,461 95% range 1,452 to 1,469 | 4,718 | Source for Science |
| Software and IT Topic | 62nd of 77 | 1,460 95% range 1,454 to 1,466 | 11,149 | 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
- Homework and maths: 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 Middle on coding votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Homework and maths: no result on hard maths problems, so we cannot say. See which models the evidence does support.
- 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
- Z.ai (Zhipu AI)
- Release date (Epoch AI)
- 11 Feb 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) |
1,446 Arena score 95% range 1,442 to 1,450, 29,255 votes |
Middle | effort: not stated, bradley-terry rating | GLM-5 lmarena · text/latest |
28 Oct 2026 | Source for GLM-5 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,438 Arena score 95% range 1,429 to 1,447, 4,850 votes |
Middle | effort: not stated, bradley-terry rating | GLM-5 lmarena · text/latest |
28 Oct 2026 | Source for GLM-5 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,461 Arena score 95% range 1,454 to 1,468, 7,624 votes |
Middle | effort: not stated, bradley-terry rating | GLM-5 lmarena · text/latest |
28 Oct 2026 | Source for GLM-5 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,440 Arena score 95% range 1,426 to 1,454, 1,694 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GLM-5 lmarena · text/latest |
28 Oct 2026 | Source for GLM-5 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,428 Arena score 95% range 1,421 to 1,434, 9,588 votes |
Middle | effort: not stated, bradley-terry rating | GLM-5 lmarena · text/latest |
28 Oct 2026 | Source for GLM-5 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,430 Arena score 95% range 1,422 to 1,438, 5,894 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GLM-5 lmarena · text/latest |
28 Oct 2026 | Source for GLM-5 Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,436 Arena score 95% range 1,427 to 1,444, 7,465 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GLM-5 lmarena · webdev/latest |
28 Oct 2026 | Source for GLM-5 Arena WebDev: building web apps score (lmarena) |
| FrontierMath Tiers 1-3 (v2) | Not enough data | |||||
| OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025, benchmark released 2024-12-19 |
80.0% share of problems solved standard error ±6.0 points |
Behind the leaders | effort: not stated, best score across scorers | glm-5 epoch · otis_mock_aime_2024_2025.csv |
12 Feb 2026 | Source for GLM-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 |
87.8% share of questions correct standard error ±2.3 points |
Behind the leaders | effort: not stated, best score across scorers | glm-5 epoch · gpqa_diamond.csv |
12 Feb 2026 | Source for GLM-5 GPQA Diamond score (epoch) · Run details for GPQA Diamond |
| SimpleQA Verified | Not enough data | |||||
| SWE-bench Verified (Epoch runs) SWE-bench Verified, benchmark released 2024-08-13, as run by Epoch AI |
72.1% share of issues resolved standard error ±2.1 points |
Behind the leaders | effort: not stated, best score across scorers | glm-5 epoch · swe_bench_verified.csv |
15 Feb 2026 | Source for GLM-5 SWE-bench Verified (Epoch runs) score (epoch) · Run details for SWE-bench Verified (Epoch runs) |
| FrontierCode (reported by Cognition) | Not enough data | |||||
Missing evidence
Not enough data for these tests:
- FrontierMath Tiers 1-3 (v2)
- SimpleQA Verified
- 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.