Benchmark menu

Model detail

GLM-5.2

A static, shareable model page that remains complete without JavaScript.

GLM-5.2

Provider: Zhipu · Public slug: z-ai-glm-5-2

Rank
15
Rank movement
Baseline
Score
36.6
Last measured
2026-07-05
Coverage
Complete coverage

Reasoning scores

XHigh
36.9
Medium
36.6
None
36.3

Generation health

XHigh4%68%28%n 25Medium13%54%33%n 24None50%38%12%n 32 Complete coverageHigh repair rateHigh failure rate

Cost summary

Mean standard list-price equivalent
$0.12
Median unique-cell cost
$0.13
Unique-cell range
$0.01–$0.26
Coverage
24 unique cells / 81 observed runs
Observed-run total
$8.92
Evidence basis
Mixed: Provider-reported + Standard list-price estimate
Mean output
31k tok
Output range
1.2k–110k tok
Token samples
81

Cost means equal-weight unique model/game/reasoning cells. Provider-account billed spend is reported separately on Charts.

Run setup

  • Overall Models: combines public reasoning variants
  • Standard GameBench code-generation prompt