Z.aiProvisional

GLM 4.7

Z.ai / GLM 4.7 · zai-org/GLM-4.7

Current GLM 4.x open-weight model to track for domestic coding, reasoning, and agent work.

Objective score

21.5

Confidence

79%

Price evidence

Pricing evidence pending

Support this model Compare trend Official source

Other primary tiers in this family

GLM 4 32B 0414 GLM 4 9B 0414 GLM 4.5 GLM 4.5 Air GLM 4.6GLM 4.7GLM 5 GLM 5.1 GLM 5.2 GLM Z1 32B 0414 GLM Z1 9B 0414 GLM Z1 Rumination 32B 0414

Scenario evidence

Six task-specific rankings

Feature development#59Obj. 21.50 · 0%Debug and repair#54Obj. 33.90 · 0%Refactoring#54Obj. 33.90 · 0%Code review#54Obj. 35.20 · 0%Large-repo agent work#61Obj. 18.30 · 0%Frontend / UI#54Obj. 33.90 · 0%

Evidence state

Signal coverage

Benchmarks: 2
Rank points: 8
Usage: 2
Agent: 0
Sources: 8

Objective evidence

Benchmarks and public signals

Swebench: —
Livecodebench: —
Aider: —
Artificial Analysis: 45.3
Openrouter Usage: 0.2
Kilo Usage: —

Persistent history

Recent ranking points

Aug 1#57 · 23

Aug 1#57 · 23

Jul 31#57 · 23

Jul 31#57 · 23

Jul 31#57 · 23

Jul 31#57 · 23

Usage signals

OpenRouter0.2%

Overall0.1%

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.

Source trail

Official Z.ai GLM-4.7 Hugging Face card is a current GLM 4.x source.Artificial Analysis Coding Agents · ok WebDev Arena · ok Kilo leaderboard · ok GLM-5 repository · ok Step 3.5 Flash model card · ok NVIDIA Nemotron 3 Ultra model card · ok GLM-4.7 model card · ok GLM-4.7 Flash model card · ok