GLM-5.3: benchmarks, price and rank
GLM-5.3 from Zhipu is 23rd of 123 rated AI models on Spezia's leaderboard, strongest on Humanity's Last Exam and CyberGym. It costs $1.20 in, $4 out per million tokens.
- 23rd of 123 rated models
- Rating 1,552
- Rated on 14 benchmarks
- Open weights
- Released Aug 14, 2026
- 1 million tokens of context
Where it is strongest
- 4th of 74 on Humanity's Last Exam
- 2nd of 15 on CyberGym
Where it falls behind
- 7th of 8 on ExploitGym
- 48th of 78 on SimpleQA Verified
- 12th of 20 on CursorBench
Price: $1.20 in, $4 out per million tokens.
Its headline results
The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.
- APEX-Agents56.6%
Long tasks written by investment banking analysts, management consultants and corporate lawyers from their own work, done across files and apps in a realistic work setup.
22nd of 56. Independent result from Epoch AI.
- Terminal-Bench 4.041.8%
Hard jobs done in a real computer terminal: building and fixing software, setting up systems, and science and engineering problems.
Independent result from LLM Stats.
- FrontierSWE30.2%
Open-ended technical projects that take hours to tens of hours, from making systems faster to building large programs and applied machine learning research. Each run gets a 20-hour budget.
12th of 21. Independent result from Epoch AI.
- Humanity's Last Exam62.5%
About 2,500 questions written by experts in more than a hundred fields to be as hard as they could make them, many needing a diagram or image.
4th of 74. The maker's own number, from Zhipu AI, via LLM Stats.
- Vending-Bench 2$8,164
The model runs a simulated vending machine business for a year on its own: finding suppliers, ordering stock, setting prices and paying the daily fees.
16th of 60. Independent result from Epoch AI.
- Toolathlon73%
Long tasks across many real apps and their tools, such as email, calendars, spreadsheets, code repositories and online stores.
7th of 37. The maker's own number, from Zhipu AI, via LLM Stats.
- CursorBench42.6%
Ambiguous coding tasks that span many files, taken from real sessions in the Cursor code editor.
12th of 20. Independent result from Epoch AI.
- DeepSWE 1.166.9%
Software engineering tasks run in the same simple agent setup for every model.
16th of 27. The maker's own number, from Zhipu AI, via LLM Stats.
- SimpleBench66.2%
Multiple-choice puzzles about everyday situations, space, time and people, written to trip up models that pattern-match instead of think. Ordinary adults do well on them.
29th of 68. Independent result from Epoch AI.
- SimpleQA Verified41%
Short factual questions with one checked answer, asked without web search.
48th of 78. Independent result from Epoch AI.
8 more results in its full profile.
Every result with its source, what it costs per task, what jumped with its release, side by side with any other model, and answers to your questions about when to use it.
Models ranked near it
How the rating works, and every benchmark it uses: the model leaderboard.