DataLearner logo

Kimi K2.6vsMiniMax-M2.7

Across 5 shared benchmarks, Kimi K2.6 leads overall: Kimi K2.6 wins 4, MiniMax-M2.7 wins 1, with 0 ties and an average score difference of +1.

Moonshot AI
Kimi K2.6

Moonshot AI · 2026-04-20 · Reasoning model

MiniMaxAI
MiniMax-M2.7

MiniMaxAI · 2026-03-18 · Reasoning model

Kimi K2.64 wins(80%)(20%)1 winMiniMax-M2.7

Benchmark scores

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

Coding and Software Engineer

Kimi K2.6 2/2
BenchmarkKimi K2.6MiniMax-M2.7Diff
SWE-Bench Pro - Public58.6018 / 62Thinking (With Tools)56.2029 / 62Thinking (With Tools)+2.40
SWE-bench Multilingual76.708 / 29Thinking (With Tools)76.509 / 29Thinking (With Tools)+0.20

AI Agent - Tool Usage

Kimi K2.6 1/1
BenchmarkKimi K2.6MiniMax-M2.7Diff
Terminal Bench 2.066.7010 / 48Thinking (With Tools)5725 / 48Thinking (With Tools)+9.70

Claw-style Agent Evaluation

MiniMax-M2.7 1/1
BenchmarkKimi K2.6MiniMax-M2.7Diff
Claw Bench80.9019 / 29Thinking (With Tools)91.705 / 29Thinking (With Tools)-10.80

General Evaluation

Kimi K2.6 1/1
BenchmarkKimi K2.6MiniMax-M2.7Diff
GPQA Diamond90.5043 / 274Thinking (No Tools)8784 / 274Thinking (No Tools)+3.50

Specs

FieldKimi K2.6MiniMax-M2.7
PublisherMoonshot AIMiniMaxAI
Release date2026-04-202026-03-18
Model typeReasoning modelReasoning model
ArchitectureMoEMoE
Parameters1T229B
Context length256K200K
Max outputNot available200K

API pricing

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

ItemKimi K2.6MiniMax-M2.7
Text input$0.95 / 1M tokens$0.3 / 1M tokens
Text output$4 / 1M tokens$1.2 / 1M tokens
Cache read$0.16 / 1M tokens$0.06 / 1M tokens
Cache write$0.95 / 1M tokens$0.375 / 1M tokens

Summary

  • Kimi K2.6leads in:Coding and Software Engineer (2/2), AI Agent - Tool Usage (1/1), General Evaluation (1/1)
  • MiniMax-M2.7leads in:Claw-style Agent Evaluation (1/1)

On average across the 5 shared benchmarks, Kimi K2.6 scores 1 higher.

Largest single-benchmark gap: Claw Bench — Kimi K2.6 80.90 vs MiniMax-M2.7 91.70 (-10.80).

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