GLM-5.2vsMiniMax M3

Across 3 shared benchmarks, GLM-5.2 leads overall: GLM-5.2 wins 3, MiniMax M3 wins 0, with 0 ties and an average score difference of +8.11.

智谱AI
GLM-5.2

智谱AI · 2026-06-13 · Reasoning model

MiniMaxAI
MiniMax M3

MiniMaxAI · 2026-06-01 · Multimodal model

GLM-5.23 wins(100%)(0%)0 winsMiniMax M3

Benchmark scores

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

AI Agent - Tool Usage

GLM-5.2 1/1
BenchmarkGLM-5.2MiniMax M3Diff
TerminalBench 2.1814 / 14Thinking High (With Tools)6611 / 14Thinking (With Tools)+15

Coding and Software Engineer

GLM-5.2 1/1
BenchmarkGLM-5.2MiniMax M3Diff
SWE-Bench Pro - Public62.105 / 44Thinking (With Tools)597 / 44Thinking (With Tools)+3.10

General Knowledge

GLM-5.2 1/1
BenchmarkGLM-5.2MiniMax M3Diff
LiveBench76.249 / 115Normal (No Tools)70.0240 / 115Deep Thinking (No Tools)+6.22

Specs

FieldGLM-5.2MiniMax M3
Publisher智谱AIMiniMaxAI
Release date2026-06-132026-06-01
Model typeReasoning modelMultimodal model
ArchitectureMoEMoE
Parameters753.33B428B
Context length1M1M
Max output128K512K

API pricing

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

ItemGLM-5.2MiniMax M3
Text input$1.4 / 1M tokens¥2.1 / 1M tokens
Text output$4.4 / 1M tokens¥8.4 / 1M tokens
Cache read$0.26 / 1M tokens¥0.42 / 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 8.11 higher.

Largest single-benchmark gap: TerminalBench 2.1 — GLM-5.2 81 vs MiniMax M3 66 (+15).

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