Claude Sonnet 5 vs Kimi K2.7 Code vs Qwen3 Coder Next

A generalist with elite coding scores against two coding specialists. The benchmark band carries SWE-bench Verified, Aider Polyglot, and LiveCodeBench side by side.Last reviewed 2026-07-17.

Claude Sonnet 5 vs Kimi K2.7 Code vs Qwen3 Coder Next

At a glance

Anthropic's fifth-generation Sonnet — near-Opus intelligence at Sonnet speed and price.

801M ctx$2.00/$10.00 per M#26/92

MoonshotAI's coding-focused Kimi model for end-to-end software engineering.

82262K ctx$0.82/$3.75 per M#20/92

Efficient coding agent with 80B parameters, only 3B active per token.

262K ctx$0.11/$0.80 per M

Demos

All demos

No shared demos for these models yet.

AI Output

All AI outputs

No captured outputs for these models yet.

Benchmarks

See rankings

Differences only

The paired significance test (McNemar, in "Measured on Idapt") appears only when exactly two models are pinned.

Reasoning

CI 72.7-84.7Provisional

CodingInsufficient data

AgenticInsufficient data

Sources:Epoch ECIEpoch AIOpenRouter

Capability

CapabilityECI80.1

Reasoning & Knowledge

Graduate Science1%90.5%Factual Recall25.0%

Math

Competition Math94.7%

Reasoning

CodingInsufficient data

AgenticInsufficient data

Sources:Epoch ECIEpoch AIOpenRouter

Smarter2%

Capability

CapabilityECI2%81.8

Reasoning & Knowledge

Graduate Science89.5%Factual Recall57%39.2%

Math

Competition Math2%96.4%

CodingInsufficient data

AgenticInsufficient data

ReasoningInsufficient data

MathInsufficient data

Sources:OpenRouter

Cheaper82%

Capability

Capability—

Reasoning & Knowledge

Graduate Science—Factual Recall—

Math

Competition Math—

Specs

Context

128K

Max output

Jun 2026

Released

262K

Context

128K

Max output

Jun 2026

Released

262K

Context

128K

Max output

Feb 2026

Released

Capabilities

Vision

Audio

Reasoning

Vision

Audio

Reasoning

Vision

Audio

Reasoning

Pricing

Differences only

Live pricing, shown before you run

Input$2.00/M tokens

Output$10.00/M tokens

Cache read$0.20/M tokens

Cache write$2.50/M tokens

Web search$0.01/search

Live pricing, shown before you run

Input$0.82/M tokens

Output$3.75/M tokens

Cache read$0.16/M tokens

Live pricing, shown before you run

Input87%$0.11/M tokens

Output79%$0.80/M tokens

Cache read56%$0.07/M tokens

Chat with Claude Sonnet 5 Go to model

Chat with Kimi K2.7 Code Go to model

Chat with Qwen3 Coder Next Go to model

Frequently asked

Which of Claude Sonnet 5, Kimi K2.7 Code, and Qwen3 Coder Next is the cheapest?

Qwen3 Coder Next has the lowest blended list price. Per 1M tokens: Claude Sonnet 5 at $2.00 in / $10.00 out; Kimi K2.7 Code at $0.82 in / $3.75 out; Qwen3 Coder Next at $0.11 in / $0.80 out.

Which of Claude Sonnet 5, Kimi K2.7 Code, and Qwen3 Coder Next has the largest context window?

Claude Sonnet 5 leads with 1M tokens. The other two: Kimi K2.7 Code at 262K, Qwen3 Coder Next at 262K.

Do Claude Sonnet 5, Kimi K2.7 Code, and Qwen3 Coder Next support image input?

Claude Sonnet 5 and Kimi K2.7 Code accept images; the third do not.

Where can I run Claude Sonnet 5, Kimi K2.7 Code, and Qwen3 Coder Next side by side?

This idapt comparison runs all three in aligned columns: the same prompt, plus benchmarks, specs, and prices per model. Open any model in chat from its column to keep working with it.

More three-way comparisons

GPT 5.6 Sol vs Claude Opus 4.8 vs Gemini 3.1 Pro Claude Fable 5 vs GPT 5.6 Sol vs Grok 4.5 GPT 5.6 Luna vs Gemini 3.5 Flash vs Claude Haiku 4.5 DeepSeek V4 Pro vs Qwen3.7 Max vs Nemotron 3 Ultra MiniMax M3 vs DeepSeek V4 Flash vs Gemini 3.1 Flash Lite Claude Sonnet 5 vs Grok Build 0.1 vs Kimi K3 Muse Spark 1.1 vs Kimi K3 vs Grok 4.5 DeepSeek V4 Flash vs Gemini 3.5 Flash vs Qwen3.7 Plus GLM 5.2 vs MiniMax M3 vs DeepSeek V4 Pro