GLM-4.7: benchmarks, price and rank
GLM-4.7 from Zhipu is 78th of 123 rated AI models on Spezia's leaderboard. It costs $0.40 in, $1.75 out per million tokens.
- 78th of 123 rated models
- Rating 994
- Rated on 11 benchmarks
- Open weights
- Released Dec 22, 2025
- 205,000 tokens of context
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 83rd of 94 on Epoch Capabilities Index
- 56th of 68 on SimpleBench
- 48th of 60 on Vending-Bench 2
Price: $0.40 in, $1.75 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.
- BrowseComp52%
Questions whose answers are hidden deep on the web and take many searches and pages to track down.
43rd of 56. The maker's own number, from Zhipu AI, via LLM Stats.
- Humanity's Last Exam42.8%
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.
26th of 74. The maker's own number, from Zhipu AI, via LLM Stats.
- Vending-Bench 2$2,377
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.
48th of 60. Independent result from Epoch AI.
- LiveCodeBench v684.9%
Programming contest problems collected after models were trained, from LeetCode, AtCoder and Codeforces.
13th of 43. The maker's own number, from Zhipu AI, via LLM Stats.
- SimpleBench47.7%
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.
56th of 68. Independent result from Epoch AI.
- SimpleQA Verified32.2%
Short factual questions with one checked answer, asked without web search.
61st of 78. Independent result from Epoch AI.
- LMArena text1,435
People put a question to two anonymous models and vote for the better answer.
58th of 107. Independent result from LMArena.
- LMArena WebDev1,435
People ask two anonymous models to build the same web page or app and vote for the better one.
64th of 98. Independent result from LMArena.
- IMO-AnswerBench82%
Problems from the International Mathematical Olympiad, the hardest contest for school students, where the model has to reach the right final answer.
12th of 18. The maker's own number, from Zhipu AI, via LLM Stats.
- SWE-bench Verified73.8%
Real bug reports and feature requests from popular open-source Python projects. The model has to change the code so the project's hidden tests pass.
17th of 56. The maker's own number, from Zhipu AI, via LLM Stats.
4 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.