Qwen 3.6 Plus PreviewvsMiniMax-M2.7

Across 5 shared benchmarks, Qwen 3.6 Plus Preview leads overall: Qwen 3.6 Plus Preview wins 3, MiniMax-M2.7 wins 2, with 0 ties and an average score difference of +4.78.

阿里巴巴
Qwen 3.6 Plus Preview

阿里巴巴 · 2026-03-31 · Chat model

MiniMaxAI
MiniMax-M2.7

MiniMaxAI · 2026-03-18 · Reasoning model

Qwen 3.6 Plus Preview3 wins(60%)(40%)2 winsMiniMax-M2.7

Benchmark scores

Grouped by capability, sorted by largest gap within each. 5 shared benchmarks.

General Knowledge

Qwen 3.6 Plus Preview 2/2
BenchmarkQwen 3.6 Plus PreviewMiniMax-M2.7Diff
HLE50.6017 / 157Thinking (With Tools)2882 / 157Thinking (No Tools)+22.60
GPQA Diamond90.4017 / 178Thinking (No Tools)8738 / 178Thinking (No Tools)+3.40

Coding and Software Engineer

Qwen 3.6 Plus Preview 1/1
BenchmarkQwen 3.6 Plus PreviewMiniMax-M2.7Diff
SWE-Bench Pro - Public56.6013 / 43Thinking (With Tools)56.2016 / 43Thinking (With Tools)+0.40

Instruction Following

MiniMax-M2.7 1/1
BenchmarkQwen 3.6 Plus PreviewMiniMax-M2.7Diff
IF Bench74.206 / 29Thinking (No Tools)765 / 29Thinking (With Tools)-1.80

Long Context

MiniMax-M2.7 1/1
BenchmarkQwen 3.6 Plus PreviewMiniMax-M2.7Diff
AA-LCR68.306 / 13Thinking (No Tools)694 / 13Thinking (With Tools)-0.70

Specs

FieldQwen 3.6 Plus PreviewMiniMax-M2.7
Publisher阿里巴巴MiniMaxAI
Release date2026-03-312026-03-18
Model typeChat modelReasoning model
ArchitectureDenseMoE
ParametersNot available229B
Context length1M200K
Max output64K200K

API pricing

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

ItemQwen 3.6 Plus PreviewMiniMax-M2.7
Text input$0.5 / 1M tokens$0.3 / 1M tokens
Text output$3 / 1M tokens$1.2 / 1M tokens
Cache read$0.05 / 1M tokens$0.06 / 1M tokens
Cache write$0.625 / 1M tokens$0.375 / 1M tokens

Summary

  • Qwen 3.6 Plus Previewleads in:General Knowledge (2/2), Coding and Software Engineer (1/1)
  • MiniMax-M2.7leads in:Instruction Following (1/1), Long Context (1/1)

On average across the 5 shared benchmarks, Qwen 3.6 Plus Preview scores 4.78 higher.

Largest single-benchmark gap: HLE — Qwen 3.6 Plus Preview 50.60 vs MiniMax-M2.7 28 (+22.60).

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