MiniMax M3vsGLM 5.1

Across 3 shared benchmarks, MiniMax M3 leads overall: MiniMax M3 wins 3, GLM 5.1 wins 0, with 0 ties and an average score difference of +4.03.

MiniMaxAI
MiniMax M3

MiniMaxAI · 2026-06-01 · Multimodal model

智谱AI
GLM 5.1

智谱AI · 2026-03-27 · Reasoning model

MiniMax M33 wins(100%)(0%)0 winsGLM 5.1

Benchmark scores

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

AI Agent - Information Search

MiniMax M3 1/1
BenchmarkMiniMax M3GLM 5.1Diff
BrowseComp83.508 / 45Thinking (With Tools + Internet)79.3013 / 45Thinking (With Tools + Internet)+4.20

AI Agent - Tool Usage

MiniMax M3 1/1
BenchmarkMiniMax M3GLM 5.1Diff
TerminalBench 2.16610 / 13Thinking (With Tools)58.7011 / 13Thinking High (With Tools)+7.30

Coding and Software Engineer

MiniMax M3 1/1
BenchmarkMiniMax M3GLM 5.1Diff
SWE-Bench Pro - Public596 / 43Thinking (With Tools)58.409 / 43Thinking (With Tools)+0.60

Specs

FieldMiniMax M3GLM 5.1
PublisherMiniMaxAI智谱AI
Release date2026-06-012026-03-27
Model typeMultimodal modelReasoning model
ArchitectureMoEMoE
Parameters428B75.4B
Context length1M200K
Max output512K125K

API pricing

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

ItemMiniMax M3GLM 5.1
Text input¥2.1 / 1M tokens$1.4 / 1M tokens
Text output¥8.4 / 1M tokens$4.4 / 1M tokens
Cache read¥0.42 / 1M tokens$4.4 / 1M tokens
Cache writeNot public$0.26 / 1M tokens

Summary

  • MiniMax M3leads in:AI Agent - Information Search (1/1), AI Agent - Tool Usage (1/1), Coding and Software Engineer (1/1)

On average across the 3 shared benchmarks, MiniMax M3 scores 4.03 higher.

Largest single-benchmark gap: TerminalBench 2.1 — MiniMax M3 66 vs GLM 5.1 58.70 (+7.30).

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