GLM-4.7

Z.ai llm

Z.ai's coding-focused flagship with interleaved thinking modes, positioned as the top open-weight coder at release.

overall ⌄

53.1

34 of 93 ranked

price · $/M tokens

0.6 / 2.2

in / out, as of 2026-07-25

to run it yourself ⌄

215 GB

minimum · 859 GB recommended

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

benchmarkpublishedmeasured
MMLU-Pro84.3
GPQA85.7
AIME 202595.7
SWE-bench73.8
HLE24.8
BrowseComp52

Cheaper, and at least as good

On a 1,000-in, 1,000-out call these cost less and rank no lower — a hard comparison to argue with, and a narrow one. Value covers what it misses.

DeepSeek V4-Flash DeepSeek$0.00042overall 59.3
DeepSeek V4-Pro DeepSeek$0.00130overall 68.3
MiniMax M3 MiniMax$0.00150overall 65.1

Lineage

↓ distill GLM-4.7-Flash
view in full graph →

Metadata

orgZ.ai
released2025-12-22
params358B
licensemit
hf idzai-org/GLM-4.7