GLM-5.2vsGLM-5

Across 4 shared benchmarks, GLM-5.2 leads overall: GLM-5.2 wins 4, GLM-5 wins 0, with 0 ties and an average score difference of +6.12.

智谱AI
GLM-5.2

智谱AI · 2026-06-13 · Reasoning model

智谱AI
GLM-5

智谱AI · 2026-02-11 · Chat model

GLM-5.24 wins(100%)(0%)0 winsGLM-5

Benchmark scores

Grouped by capability, sorted by largest gap within each. 4 shared benchmarks.

General Knowledge

GLM-5.2 2/2
BenchmarkGLM-5.2GLM-5Diff
GPQA Diamond91.2015 / 179Thinking (No Tools)8644 / 179Thinking (No Tools)+5.20
HLE54.708 / 159Thinking (With Tools)50.4019 / 159+4.30

Math and Reasoning

GLM-5.2 2/2
BenchmarkGLM-5.2GLM-5Diff
IMO-AnswerBench911 / 20Thinking (No Tools)82.5014 / 20Thinking (No Tools)+8.50
AIME 202699.201 / 15Thinking (No Tools)92.708 / 15Thinking (No Tools)+6.50

Specs

FieldGLM-5.2GLM-5
Publisher智谱AI智谱AI
Release date2026-06-132026-02-11
Model typeReasoning modelChat model
ArchitectureMoEMoE
Parameters753.33B744B
Context length1M200K
Max output128K128K

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemGLM-5.2GLM-5
Text input$1.4 / 1M tokens$1 / 1M tokens
Text output$4.4 / 1M tokens$3.2 / 1M tokens
Cache read$0.26 / 1M tokensNot public
Cache writeNot public$0.2 / 1M tokens

Summary

  • GLM-5.2leads in:General Knowledge (2/2), Math and Reasoning (2/2)

On average across the 4 shared benchmarks, GLM-5.2 scores 6.12 higher.

Largest single-benchmark gap: IMO-AnswerBench — GLM-5.2 91 vs GLM-5 82.50 (+8.50).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.