Compare models

Context, limits, capabilities, price and use cases side by side — up to 4 models at a time. The URL holds your selection, so you can share it.

GLM-4.7GLM-5 Add a modelChat with these 2

AttributeHide identical rows	GLM-4.7z-ai/glm-4.7	GLM-5z-ai/glm-5
Specs
Context window	200K	200K
Max output	128K	128K
Input modalities	Text	Text
Output modalities	Text	Text
Capabilities
Streaming	Supported	Supported
Tool calling	Supported	Supported
Structured output (JSON)	Supported	Supported
Image input	Not supported	Not supported
Thinking mode	Supported	Supported
Price / 1M tokens
Input	$ 0.47>= 32K$ 0.62	$ 0.60>= 32K$ 0.80
Output	$ 2.16>= 32K$ 2.47	$ 3.00>= 32K$ 3.40
Cache read	$ 0.10>= 32K$ 0.13	$ 0.16>= 32K$ 0.20
Cache write	$ 0.47>= 32K$ 0.62	$ 0.60>= 32K$ 0.80
What it is good at
Best for	Agentic coding Search and research	System engineering
Published benchmarks
Terminal-Bench 2.0pass_rate	41%(setup not fully disclosed)	56.2%(setup not fully disclosed)
BrowseComp (with tools)accuracy	67%(setup not fully disclosed)	—
LiveCodeBench v6pass_rate	84.9%(setup not fully disclosed)	—
SWE-Bench Verifiedresolved_rate	73.8%(setup not fully disclosed)	77.8%(setup not fully disclosed)
Humanity's Last Examaccuracy	42.8%(setup not fully disclosed)	—
τ²-Benchscore	84.7(setup not fully disclosed)	—