GLM-5.1
Made by Z.ai (Zhipu AI), released 7 Apr 2026. Epoch AI lists its access as “Open weights (unrestricted)”. Appears solid at coding and writing among the models listed here.
In short
What it does well
- Coding: Strong (38th of 77 listed models)
- Writing: Strong (28th of 77 listed models)
Where it falls short
- Knowledge: Behind the leaders (37th of 43 listed models)
- Maths: Behind the leaders (43rd of 43 listed models)
What we don't know yet
- 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
- StrongHow often people preferred its answers to writing prompts. 1,453 on Arena's scale · Source for GLM-5.1 writing score (lmarena)
- Coding
- StrongHow often people preferred its answers to coding questions. 1,486 on Arena's scale · Source for GLM-5.1 coding score (lmarena)
- Maths
- Behind the leadersHow many very hard maths problems it solved. 24.9% · Source for GLM-5.1 maths score (epoch)
- Knowledge
- Behind the leadersHow many short factual questions it answered correctly. 34.0% · Source for GLM-5.1 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 | 40th of 77 | 1,478 95% range 1,471 to 1,486 | 7,111 | Source for Expert-level prompts |
| Hard prompts Kind of request | 38th of 77 | 1,473 95% range 1,469 to 1,477 | 43,616 | Source for Hard prompts |
| Long prompts Kind of request | 35th of 77 | 1,467 95% range 1,462 to 1,472 | 29,944 | Source for Long prompts |
| Longer conversations Kind of request | 27th of 77 | 1,472 95% range 1,466 to 1,479 | 10,549 | Source for Longer conversations |
| Chinese Language | 29th of 76 | 1,514 95% range 1,505 to 1,524 | 4,675 | Source for Chinese |
| English prompts Language | 26th of 77 | 1,475 95% range 1,471 to 1,480 | 28,384 | Source for English prompts |
| French Language | 42nd of 72 | 1,470 95% range 1,457 to 1,484 | 2,433 | Source for French |
| German Language | 26th of 55 | 1,466 95% range 1,447 to 1,484 | 1,090 | Source for German |
| Japanese Language | 29th of 54 | 1,440 95% range 1,419 to 1,461 | 959 | Source for Japanese |
| Korean Language | 31st of 54 | 1,423 95% range 1,405 to 1,441 | 1,247 | Source for Korean |
| Non-English prompts Language | 36th of 77 | 1,449 95% range 1,444 to 1,453 | 38,380 | Source for Non-English prompts |
| Russian Language | 41st of 77 | 1,455 95% range 1,448 to 1,462 | 8,091 | Source for Russian |
| Spanish Language | 28th of 70 | 1,469 95% range 1,455 to 1,482 | 2,220 | Source for Spanish |
| Entertainment, sport and media Topic | 29th of 77 | 1,442 95% range 1,436 to 1,448 | 15,875 | Source for Entertainment, sport and media |
| Law and government Topic | 38th of 76 | 1,466 95% range 1,457 to 1,474 | 5,225 | Source for Law and government |
| Medicine and health Topic | 29th of 75 | 1,474 95% range 1,465 to 1,483 | 4,717 | Source for Medicine and health |
| Science Topic | 31st of 77 | 1,479 95% range 1,472 to 1,485 | 10,954 | Source for Science |
| Software and IT Topic | 38th of 77 | 1,484 95% range 1,479 to 1,488 | 26,126 | 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 Behind the leaders 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)
- 7 Apr 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) |
1,463 Arena score 95% range 1,459 to 1,466, 66,771 votes |
Strong | effort: not stated, bradley-terry rating | GLM-5.1 lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.1 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,453 Arena score 95% range 1,446 to 1,459, 13,020 votes |
Strong | effort: not stated, bradley-terry rating | GLM-5.1 lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.1 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,486 Arena score 95% range 1,481 to 1,491, 18,059 votes |
Strong | effort: not stated, bradley-terry rating | GLM-5.1 lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.1 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,473 Arena score 95% range 1,462 to 1,484, 3,303 votes |
Strong | effort: not stated, bradley-terry rating | GLM-5.1 lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.1 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,452 Arena score 95% range 1,448 to 1,457, 23,325 votes |
Middle | effort: not stated, bradley-terry rating | GLM-5.1 lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.1 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,453 Arena score 95% range 1,447 to 1,460, 12,773 votes |
Strong | effort: not stated, bradley-terry rating | GLM-5.1 lmarena · text/latest |
28 Oct 2026 | Source for GLM-5.1 Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,508 Arena score 95% range 1,501 to 1,515, 10,647 votes |
Middle | effort: not stated, bradley-terry rating | GLM-5.1 lmarena · webdev/latest |
28 Oct 2026 | Source for GLM-5.1 Arena WebDev: building web apps score (lmarena) |
| FrontierMath Tiers 1-3 (v2) FrontierMath Tiers 1-3 v2 (private set), benchmark released 2026-06-12 |
24.9% share of problems solved standard error ±2.6 points |
Behind the leaders | effort: none, best score across scorers | glm-5.1_none epoch · frontiermath_tiers_1_3_v2.csv |
28 Aug 2026 | Source for GLM-5.1 FrontierMath Tiers 1-3 (v2) score (epoch) · Run details for FrontierMath Tiers 1-3 (v2) |
| OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025, benchmark released 2024-12-19 |
93.3% share of problems solved standard error ±3.8 points |
Middle | effort: not stated, best score across scorers | glm-5.1 epoch · otis_mock_aime_2024_2025.csv |
10 Aug 2026 | Source for GLM-5.1 OTIS Mock AIME 2024-2025 score (epoch) · Run details for OTIS Mock AIME 2024-2025 |
| GPQA Diamond GPQA Diamond, benchmark released 2023-11-20 |
89.9% share of questions correct standard error ±2.1 points |
Middle | effort: not stated, best score across scorers | glm-5.1 epoch · gpqa_diamond.csv |
10 Aug 2026 | Source for GLM-5.1 GPQA Diamond score (epoch) · Run details for GPQA Diamond |
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
34.0% share of questions correct standard error ±1.5 points |
Behind the leaders | effort: not stated, best score across scorers | glm-5.1 epoch · simpleqa_verified.csv |
27 Aug 2026 | Source for GLM-5.1 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 |
74.2% share of issues resolved standard error ±2.0 points |
Middle | effort: not stated, best score across scorers | glm-5.1 epoch · swe_bench_verified.csv |
15 May 2026 | Source for GLM-5.1 SWE-bench Verified (Epoch runs) score (epoch) No public run log in the data file. |
| FrontierCode (reported by Cognition) | Not enough data | |||||
Missing evidence
Not enough data for these tests:
- 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.