DataLearner logo

MiniMax-M2.7vsGLM-5

Across 10 shared benchmarks, MiniMax-M2.7 leads overall: MiniMax-M2.7 wins 5, GLM-5 wins 4, with 1 ties and an average score difference of -2.91.

MiniMaxAI
MiniMax-M2.7

MiniMaxAI · 2026-03-18 · Reasoning model

智谱AI
GLM-5

智谱AI · 2026-02-11 · Chat model

MiniMax-M2.75 wins(50%)Ties1(40%)4 winsGLM-5

Benchmark scores

Grouped by capability, sorted by largest gap within each. 10 shared benchmarks.

General Knowledge

GLM-5 2/3
BenchmarkMiniMax-M2.7GLM-5Diff
HLE2896 / 172Thinking (No Tools)50.4025 / 172-22.40
LiveBench63.4956 / 115Deep Thinking (No Tools)68.8543 / 115Normal (No Tools)-5.36
GPQA Diamond8742 / 187Thinking (No Tools)8648 / 187Thinking (No Tools)+1

Agent Level Benchmark

GLM-5 2/2
BenchmarkMiniMax-M2.7GLM-5Diff
τ²-Bench - Telecom8524 / 35Thinking (With Tools)985 / 35-13
Terminal Bench Hard395 / 13Thinking (With Tools)432 / 13-4

Claw-style Agent Evaluation

MiniMax-M2.7 1/2
BenchmarkMiniMax-M2.7GLM-5Diff
Pinch Bench87.109 / 37Thinking (With Tools)86.4012 / 37Thinking (With Tools)+0.70
Claw Bench91.705 / 29Thinking (With Tools)91.705 / 29Thinking (With Tools)

Instruction Following

MiniMax-M2.7 1/1
BenchmarkMiniMax-M2.7GLM-5Diff
IF Bench766 / 30Thinking (With Tools)7211 / 30+4

Long Context

MiniMax-M2.7 1/1
BenchmarkMiniMax-M2.7GLM-5Diff
AA-LCR696 / 15Thinking (With Tools)6314 / 15Thinking (No Tools)+6

Productivity Knowledge

MiniMax-M2.7 1/1
BenchmarkMiniMax-M2.7GLM-5Diff
GDPval-AA5013 / 21Thinking (No Tools)4614 / 21Thinking (No Tools)+4

Specs

FieldMiniMax-M2.7GLM-5
PublisherMiniMaxAI智谱AI
Release date2026-03-182026-02-11
Model typeReasoning modelChat model
ArchitectureMoEMoE
Parameters229B744B
Context length200K200K
Max output200K128K

API pricing

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

ItemMiniMax-M2.7GLM-5
Text input$0.3 / 1M tokens$1 / 1M tokens
Text output$1.2 / 1M tokens$3.2 / 1M tokens
Cache read$0.06 / 1M tokensNot public
Cache write$0.375 / 1M tokens$0.2 / 1M tokens

Summary

  • MiniMax-M2.7leads in:Claw-style Agent Evaluation (1/2), Instruction Following (1/1), Long Context (1/1), Productivity Knowledge (1/1)
  • GLM-5leads in:General Knowledge (2/3), Agent Level Benchmark (2/2)

On average across the 10 shared benchmarks, GLM-5 scores 2.91 higher.

Largest single-benchmark gap: HLE — MiniMax-M2.7 28 vs GLM-5 50.40 (-22.40).

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