Z.aiProvisional

GLM 5.2

Z.ai / GLM 5.2 · zai-org/GLM-5.2

Chinese open-weight long-horizon agentic engineering model with 1M-token context.

Objective score

46.2

Confidence

86%

Price evidence

Open weights; hosted pricing varies

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 4.6 GLM 4.7 GLM 5 GLM 5.1GLM 5.2GLM 5.3 GLM Z1 32B 0414 GLM Z1 9B 0414 GLM Z1 Rumination 32B 0414

Scenario evidence

Six task-specific rankings

Feature development#9Obj. 46.20 · 0%Debug and repair#9Obj. 54.60 · 0%Refactoring#11Obj. 52.40 · 0%Code review#12Obj. 55.10 · 0%Large-repo agent work#12Obj. 43.50 · 0%Frontend / UI#13Obj. 51.70 · 0%

Evidence state

Signal coverage

Benchmarks: 3
Rank points: 7
Usage: 3
Agent: 0
Sources: 6

Objective evidence

Benchmarks and public signals

Swebench: 62.1
Livecodebench: —
Aider: —
Artificial Analysis: 68.8
Openrouter Usage: 2.2
Kilo Usage: —

Persistent history

Recent ranking points

Sep 15#17 · 44

Sep 15#17 · 44

Sep 15#17 · 44

Sep 14#18 · 44

Sep 14#18 · 44

Sep 14#18 · 44

Usage signals

Overall10.1%

OpenRouter coding6.6%

OpenRouter2.2%

Agent and tool signals

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

Source trail

Official GLM-5 repo describes GLM-5.2 coding gains and 1M-token context.Artificial Analysis Coding Agents · ok WebDev Arena · ok Kilo leaderboard · ok OpenRouter rankings · ok Mistral model overview · ok GLM-5 repository · ok