GLM-5.2vsKimi K2.7 Code

Across 3 shared benchmarks, GLM-5.2 leads overall: GLM-5.2 wins 3, Kimi K2.7 Code wins 0, with 0 ties and an average score difference of +10.44.

智谱AI
GLM-5.2

智谱AI · 2026-06-13 · Reasoning model

Moonshot AI
Kimi K2.7 Code

Moonshot AI · 2026-06-12 · Coding model

GLM-5.23 wins(100%)(0%)0 winsKimi K2.7 Code

Benchmark scores

Grouped by capability, sorted by largest gap within each. 3 shared benchmarks.

AI Agent - Tool Usage

GLM-5.2 1/1
BenchmarkGLM-5.2Kimi K2.7 CodeDiff
TerminalBench 2.1814 / 14Thinking High (With Tools)67.0410 / 14Thinking (With Tools)+13.96

Coding and Software Engineer

GLM-5.2 1/1
BenchmarkGLM-5.2Kimi K2.7 CodeDiff
DeepSWE445 / 9Deep Thinking (With Tools)317 / 9Normal (With Tools)+13

General Knowledge

GLM-5.2 1/1
BenchmarkGLM-5.2Kimi K2.7 CodeDiff
LiveBench76.249 / 115Normal (No Tools)71.8930 / 115Normal (No Tools)+4.35

Specs

FieldGLM-5.2Kimi K2.7 Code
Publisher智谱AIMoonshot AI
Release date2026-06-132026-06-12
Model typeReasoning modelCoding model
ArchitectureMoEMoE
Parameters753.33B1T
Context length1M256K
Max output128KNot available

API pricing

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

ItemGLM-5.2Kimi K2.7 Code
Text input$1.4 / 1M tokens$0.95 / 1M tokens
Text output$4.4 / 1M tokens$4 / 1M tokens
Cache read$0.26 / 1M tokens$0.19 / 1M tokens

Summary

  • GLM-5.2leads in:AI Agent - Tool Usage (1/1), Coding and Software Engineer (1/1), General Knowledge (1/1)

On average across the 3 shared benchmarks, GLM-5.2 scores 10.44 higher.

Largest single-benchmark gap: TerminalBench 2.1 — GLM-5.2 81 vs Kimi K2.7 Code 67.04 (+13.96).

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