DataLearner logo

Kimi K2.7 CodevsKimi K2.5

Across 3 shared benchmarks, Kimi K2.7 Code leads overall: Kimi K2.7 Code wins 3, Kimi K2.5 wins 0, with 0 ties and an average score difference of +8.51.

Moonshot AI
Kimi K2.7 Code

Moonshot AI · 2026-06-12 · Coding model

Moonshot AI
Kimi K2.5

Moonshot AI · 2026-01-27 · Multimodal model

Kimi K2.7 Code3 wins(100%)(0%)0 winsKimi K2.5

Benchmark scores

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

AI Agent - Tool Usage

Kimi K2.7 Code 1/1
BenchmarkKimi K2.7 CodeKimi K2.5Diff
MCP-Atlas7619 / 41Thinking (With Tools)64.4032 / 41Normal (With Tools)+11.60

Commonsense Reasoning

Kimi K2.7 Code 1/1
BenchmarkKimi K2.7 CodeKimi K2.5Diff
SimpleBench57.9036 / 92Thinking (No Tools)46.8052 / 92Thinking (No Tools)+11.10

General Knowledge

Kimi K2.7 Code 1/1
BenchmarkKimi K2.7 CodeKimi K2.5Diff
LiveBench71.8930 / 115Normal (No Tools)69.0742 / 115Thinking (No Tools)+2.82

Specs

FieldKimi K2.7 CodeKimi K2.5
PublisherMoonshot AIMoonshot AI
Release date2026-06-122026-01-27
Model typeCoding modelMultimodal model
ArchitectureMoEMoE
Parameters1T1T
Context length256K256K
Max outputNot available16K

API pricing

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

ItemKimi K2.7 CodeKimi K2.5
Text input$0.95 / 1M tokens$0.6 / 1M tokens
Text output$4 / 1M tokens$3 / 1M tokens
Cache read$0.19 / 1M tokens$0.1 / 1M tokens

Summary

  • Kimi K2.7 Codeleads in:AI Agent - Tool Usage (1/1), Commonsense Reasoning (1/1), General Knowledge (1/1)

On average across the 3 shared benchmarks, Kimi K2.7 Code scores 8.51 higher.

Largest single-benchmark gap: MCP-Atlas — Kimi K2.7 Code 76 vs Kimi K2.5 64.40 (+11.60).

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