Kimi K2.6vsKimi K2

Across 4 shared benchmarks, Kimi K2.6 leads overall: Kimi K2.6 wins 4, Kimi K2 wins 0, with 0 ties and an average score difference of +32.25.

Moonshot AI
Kimi K2.6

Moonshot AI · 2026-04-20 · Reasoning model

Moonshot AI
Kimi K2

Moonshot AI · 2025-07-11 · Chat model

Kimi K2.64 wins(100%)(0%)0 winsKimi K2

Benchmark scores

Grouped by capability, sorted by largest gap within each. 4 shared benchmarks.

Coding and Software Engineer

Kimi K2.6 2/2
BenchmarkKimi K2.6Kimi K2Diff
LiveCodeBench89.607 / 120Thinking (No Tools)53.7086 / 120+35.90
SWE-bench Verified80.2013 / 108Thinking (With Tools)51.8088 / 108+28.40

General Knowledge

Kimi K2.6 2/2
BenchmarkKimi K2.6Kimi K2Diff
HLE549 / 157Thinking (With Tools + Internet)4.70154 / 157+49.30
GPQA Diamond90.5016 / 178Thinking (No Tools)75.1093 / 178+15.40

Specs

FieldKimi K2.6Kimi K2
PublisherMoonshot AIMoonshot AI
Release date2026-04-202025-07-11
Model typeReasoning modelChat model
ArchitectureMoEMoE
Parameters1T1T
Context length256K131K
Max outputNot available131K

API pricing

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

ItemKimi K2.6Kimi K2
Text input$0.95 / 1M tokensNot public
Text output$4 / 1M tokensNot public
Cache read$0.16 / 1M tokensNot public
Cache write$0.95 / 1M tokensNot public

One or both models have incomplete public pricing.

Summary

  • Kimi K2.6leads in:Coding and Software Engineer (2/2), General Knowledge (2/2)

On average across the 4 shared benchmarks, Kimi K2.6 scores 32.25 higher.

Largest single-benchmark gap: HLE — Kimi K2.6 54 vs Kimi K2 4.70 (+49.30).

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