DataLearner logo

Kimi K2.5vsKimi K2 Thinking

Kimi K2.5 and Kimi K2 Thinking are tied across 6 shared benchmarks: Kimi K2.5 leads on 3, Kimi K2 Thinking leads on 3, with 0 ties and an average score difference of -7.35.

Moonshot AI
Kimi K2.5

Moonshot AI · 2026-01-27 · Multimodal model

Moonshot AI
Kimi K2 Thinking

Moonshot AI · 2025-11-06 · Reasoning model

Kimi K2.53 wins(50%)(50%)3 winsKimi K2 Thinking

Benchmark scores

Grouped by capability, sorted by largest gap within each. 6 shared benchmarks.

Coding and Software Engineer

Kimi K2.5 2/2
BenchmarkKimi K2.5Kimi K2 ThinkingDiff
SWE-bench Verified76.8030 / 116Thinking (With Tools)71.3056 / 116Thinking (With Tools)+5.50
LiveCodeBench8529 / 250Thinking (No Tools)83.1040 / 250Thinking (No Tools)+1.90

General Knowledge

Even 2/2
BenchmarkKimi K2.5Kimi K2 ThinkingDiff
LiveBench69.0741 / 117Thinking (No Tools)61.5965 / 117Thinking (No Tools)+7.48
MMLU Pro78.5071 / 176Thinking (No Tools)84.6035 / 176Thinking (No Tools)-6.10

Claw-style Agent Evaluation

Kimi K2 Thinking 1/1
BenchmarkKimi K2.5Kimi K2 ThinkingDiff
Claw Bench81.7018 / 29Thinking (With Tools)82.5017 / 29Thinking (With Tools)-0.80

Writing and Creative Capabilities

Kimi K2 Thinking 1/1
BenchmarkKimi K2.5Kimi K2 ThinkingDiff
Creative Writing1,57643 / 106Normal (No Tools)1,62835 / 106Normal (No Tools)-52.10

Specs

FieldKimi K2.5Kimi K2 Thinking
PublisherMoonshot AIMoonshot AI
Release date2026-01-272025-11-06
Model typeMultimodal modelReasoning model
ArchitectureMoEMoE
Parameters1T1T
Context length256K256K
Max output16KNot available

API pricing

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

ItemKimi K2.5Kimi K2 Thinking
Text input$0.6 / 1M tokens$0.6 / 1M tokens
Text output$3 / 1M tokens$2.5 / 1M tokens
Cache read$0.1 / 1M tokens$0.3 / 1M tokens
Cache writeNot public$0.6 / 1M tokens

Summary

  • Kimi K2.5leads in:Coding and Software Engineer (2/2)
  • Kimi K2 Thinkingleads in:Claw-style Agent Evaluation (1/1), Writing and Creative Capabilities (1/1)
  • Tied in:General Knowledge

On average across the 6 shared benchmarks, Kimi K2 Thinking scores 7.35 higher.

Largest single-benchmark gap: Creative Writing — Kimi K2.5 1,576 vs Kimi K2 Thinking 1,628 (-52.10).

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