GLM-4.7
Made by Z.ai (Zhipu AI), released 22 Dec 2025. 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: Behind the leaders (65th of 77 listed models)
- Knowledge: Behind the leaders (40th of 43 listed models)
- Writing: Behind the leaders (66th of 77 listed models)
What we don't know yet
- Hard maths problems: Not enough data
- Fixing real software bugs: 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
- Behind the leadersHow often people preferred its answers to writing prompts. 1,401 on Arena's scale · Source for GLM-4.7 writing score (lmarena)
- Coding
- Behind the leadersHow often people preferred its answers to coding questions. 1,454 on Arena's scale · Source for GLM-4.7 coding score (lmarena)
- Maths
- Not enough dataNo result yet for hard maths problems.
- Knowledge
- Behind the leadersHow many short factual questions it answered correctly. 32.2% · Source for GLM-4.7 knowledge score (epoch)
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
- Medicine and health: 32nd of 75 on medicine and health questions, against 66th of 77 overall. Source for Medicine and health
- Chinese: 45th of 76 on questions asked in Chinese, against 66th 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 | 74th of 77 | 1,424 95% range 1,403 to 1,444 | 807 | Source for Expert-level prompts |
| Hard prompts Kind of request | 67th of 77 | 1,443 95% range 1,435 to 1,451 | 6,788 | Source for Hard prompts |
| Long prompts Kind of request | 64th of 77 | 1,432 95% range 1,422 to 1,443 | 3,260 | Source for Long prompts |
| Longer conversations Kind of request | 56th of 77 | 1,446 95% range 1,432 to 1,459 | 1,928 | Source for Longer conversations |
| Chinese Language | 45th of 76 | 1,495 95% range 1,477 to 1,513 | 1,020 | Source for Chinese |
| English prompts Language | 52nd of 77 | 1,453 95% range 1,444 to 1,462 | 5,027 | Source for English prompts |
| French Language | 65th of 72 | 1,432 95% range 1,398 to 1,465 | 306 | Source for French |
| Non-English prompts Language | 69th of 77 | 1,417 95% range 1,410 to 1,424 | 7,212 | Source for Non-English prompts |
| Russian Language | 65th of 77 | 1,423 95% range 1,410 to 1,437 | 1,639 | Source for Russian |
| Spanish Language | 58th of 70 | 1,434 95% range 1,404 to 1,465 | 345 | Source for Spanish |
| Entertainment, sport and media Topic | 66th of 77 | 1,401 95% range 1,389 to 1,413 | 2,420 | Source for Entertainment, sport and media |
| Law and government Topic | 59th of 76 | 1,444 95% range 1,426 to 1,463 | 969 | Source for Law and government |
| Medicine and health Topic | 32nd of 75 | 1,469 95% range 1,449 to 1,489 | 826 | Source for Medicine and health |
| Science Topic | 52nd of 77 | 1,458 95% range 1,445 to 1,470 | 2,141 | Source for Science |
| Software and IT Topic | 67th of 77 | 1,453 95% range 1,444 to 1,463 | 4,116 | 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.
Where an alternative might be more suitable
- Writing and creating content: rated Behind the leaders on writing votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Coding and building things: rated Behind the leaders 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: 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)
- 22 Dec 2025
- 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) |
1,435 Arena score 95% range 1,429 to 1,441, 12,239 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GLM-4.7 lmarena · text/latest |
28 Oct 2026 | Source for GLM-4.7 Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,401 Arena score 95% range 1,388 to 1,414, 1,960 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GLM-4.7 lmarena · text/latest |
28 Oct 2026 | Source for GLM-4.7 Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,454 Arena score 95% range 1,442 to 1,466, 2,478 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GLM-4.7 lmarena · text/latest |
28 Oct 2026 | Source for GLM-4.7 Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,424 Arena score 95% range 1,404 to 1,444, 738 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GLM-4.7 lmarena · text/latest |
28 Oct 2026 | Source for GLM-4.7 Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,412 Arena score 95% range 1,402 to 1,423, 3,300 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GLM-4.7 lmarena · text/latest |
28 Oct 2026 | Source for GLM-4.7 Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,429 Arena score 95% range 1,417 to 1,441, 2,292 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GLM-4.7 lmarena · text/latest |
28 Oct 2026 | Source for GLM-4.7 Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,435 Arena score 95% range 1,423 to 1,447, 3,948 votes |
Behind the leaders | effort: not stated, bradley-terry rating | GLM-4.7 lmarena · webdev/latest |
28 Oct 2026 | Source for GLM-4.7 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 |
83.3% share of problems solved standard error ±4.8 points |
Behind the leaders | effort: not stated, best score across scorers | glm-4.7 epoch · otis_mock_aime_2024_2025.csv |
29 Jan 2026 | Source for GLM-4.7 OTIS Mock AIME 2024-2025 score (epoch) · Run details for OTIS Mock AIME 2024-2025 |
| GPQA Diamond GPQA Diamond, benchmark released 2023-11-20 |
83.3% share of questions correct standard error ±2.4 points |
Behind the leaders | effort: not stated, best score across scorers | glm-4.7 epoch · gpqa_diamond.csv |
29 Jan 2026 | Source for GLM-4.7 GPQA Diamond score (epoch) · Run details for GPQA Diamond |
| SimpleQA Verified SimpleQA Verified, benchmark released 2025-09-09 |
32.2% share of questions correct standard error ±1.5 points |
Behind the leaders | effort: not stated, best score across scorers | glm-4.7 epoch · simpleqa_verified.csv |
27 Aug 2026 | Source for GLM-4.7 SimpleQA Verified score (epoch) · Run details for SimpleQA Verified |
| SWE-bench Verified (Epoch runs) | Not enough data | |||||
| FrontierCode (reported by Cognition) | Not enough data | |||||
Missing evidence
Not enough data for these tests:
- FrontierMath Tiers 1-3 (v2)
- SWE-bench Verified (Epoch runs)
- 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.