BenchLeader
Menu
LeaderboardsModelsProvidersBenchmarksCompareReleases3BlogMethodology
Zhipu AIAuto-detected

Glm 4 0520

Glm 4 0520 is a Zhipu AI proprietary model. It is not yet ranked: 3 independent results so far, and the index needs at least five across two categories. Last measured 2 Sept 2026.

Blended price
–
Output speed
–
First answer
–
Context
–
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Reasoning43
  2. Coding43
  3. Human preference43

Versions

Zhipu AI has shipped 10 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

ModelReleasedIndexRank
GLM 5.3max14 Aug 202660.0#96
GLM 5.2max16 Jun 202657.7#136
GLM 5.17 Apr 202660.2#93
GLM 4.722 Dec 202555.1#187
GLM-4.528 Jul 202550.4#295
GLM-5–59.1#107
GLM-4.6thinking–52.3#259
Glm 4 0520this page–––
GLM-4.5–––
GLM-4.6–––

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

BenchmarkdefaultSource
LMArena Hard Prompts1278#261LMArena

Coding

BenchmarkdefaultSource
LMArena Coding1309#255LMArena

Human preference

BenchmarkdefaultSource
LMArena Text1273#262LMArena

See also

All Zhipu AI models

Data as of 10 Sept 2026. Compare with another model.