GLM-5.3-Flash
Very cheap MIT model, 13th on arena.ai Math; for coding and agents MiMo-V2.6-Pro ranks higher for less per task.
Should you use it?
Pick it if
Developers who want a cheap, MIT-licensed model for maths-heavy or bulk work through an API or their own servers.
Best for: Cheap maths-heavy or bulk work through an API or your own servers (Chat models Top 20)
Skip it if
Coding or agent work matters most; MiMo-V2.6-Pro ranks 19 on WebDev at $0.13 per task.
You give up: Mid-table for coding and weak at creative writing; hosting needs a server
The short version
- What this is
- A 320B-parameter mixture-of-experts model from Z.ai (18B active), MIT licensed, that reads text and images.
- Why it matters
- It gives near-top maths results for a small fraction of the usual token price, and you can host it yourself.
- Rank 13 of 400 on arena.ai Math; rank 25 on Expert and 26 on WebDev s1 s2 s4.
- $0.15 / $0.50 per 1M tokens on Z.ai, $0.25 per Artificial Analysis task s3 s7.
- MIT weights, but you need server GPUs to run it yourself s6.
Good at
Our take
GLM-5.3-Flash earns its page on price. It sits 13th of 400 on arena.ai Math s1, close to Google's Flash models, at $0.50 per 1M output tokens on Z.ai s7. Among the models we review, nothing cheaper scores as well for data work, which we judge from maths results as a proxy. The Math rank rests on 1,396 votes with a wide spread (1 to 54), so it may move.
Outside maths it is a solid middle pick, not a leader. For coding and agent work, MiMo-V2.6-Pro ranks higher on WebDev and Expert and costs less per Artificial Analysis task, $0.13 against $0.25 s3. Z.ai says it beats GLM-5.2 at a tenth of the price s6; that is the maker's claim, not a test we can check. Arena.ai lists a lower token price ($0.06 / $0.20) than Z.ai's own page s1 s7; we quote Z.ai's.
Scores by job
A score from 0 to 100 per job, against everything available today. Overall 67 across 3 jobs, the average of the job scores.
New to this? What the scores and labels mean
- 0 to 100
- Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
- Our verdict
- Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
- First look
- Just released. We say what it is and whether to bother, and give it a score once public results exist.
- No score yet
- None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
- Best buy
- Nothing cheaper scores as well for that job.
- Best free
- The best score for that job that costs nothing, through a free plan or by running on your own computer.
- Pay as you go
- No monthly plan: you pay for each use, usually through a developer account.
- Checked
- The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
- AI model
- The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
- Open source
- Free to download and run on your own computer, so nothing leaves your machine.
#2 of the 2 we have scored for this job.
From blind votes (Arena) and independent tests (Epoch AI) · Arena data, CC BY 4.0, Epoch AI data, CC BY 4.0
1 source so farData read 20 Oct
#10 of the 15 we have scored for this job.
From blind votes (Arena) and independent tests (Epoch AI) · Arena data, CC BY 4.0, Epoch AI data, CC BY 4.0
2 sourcesData read 20 Oct
#18 of the 21 we have scored for this job.
From blind votes (Arena) · Arena data, CC BY 4.0
1 source so farData read 20 Oct
Alternatives
Better or cheaper for data, from our scores, then the ones we'd also look at. The same kind of product comes first.
- Gemini 3.8 FlashBetterText model85$19.99 a monthScores 85 in data, against 79 here; $19.99 a month. Scores 98 for data and 91 for writing, against 94 for data here, at a higher token price. Side by side
- MiMo-V2.6-ProText model#13AgentsFreeHigher on WebDev and Expert, and cheaper per Intelligence Index task ($0.13). Side by side
Value for money
Where it sits in data: higher is a better score, further left is cheaper. Green dots are the Best buys.
Evidence
Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.
How we scored this
The data, research and coding scores are our own, built from public data: blind votes on Arena and, where they cover the job, Epoch AI's independent tests. How we combine them is our method and we don't publish it.
Public leaderboardIndependent test
Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.
No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score
Sources 10
- s10Z.ai chat app
- s1arena.ai Text: Math leaderboard
- s2arena.ai Text: Expert leaderboard
- s3Artificial Analysis LLM leaderboard
- s4arena.ai Code Arena: WebDev leaderboard
- s5arena.ai Text: Coding leaderboard
- s6Hugging Face: zai-org/GLM-5.3-Flash model card
- s7Z.ai pricing
- s8Z.ai privacy policy and API data processing terms
- s9arena.ai Text: Creative Writing leaderboard
Something here out of date or wrong? Report a mistake and we will check it against the source.
History 2 changes
Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.
- New: Data ratedNew: Research ratedNew: Coding ratedReviewed: data, research, coding.
- Plainer how-to-get-it wording; no rating change.
Use it well 4 guides on this site
Pages on this site that help with the jobs above.