Claude Sonnet 5 vs Grok Build 0.1 vs Kimi K3

Models that run tools well: the benchmark band leads with Terminal-Bench and the agent-loop demos show real multi-step work where captures exist.Last reviewed 2026-09-09.

Claude Sonnet 5 vs Grok Build 0.1 vs Kimi K3

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

xAI's agentic build model for autonomous software engineering.

256K ctx$1.00/$2.00 per M

MoonshotAI's 2.8T-parameter flagship for complex coding, knowledge work, and long-horizon agent runs.

1.0M ctx$0.30/$11.94 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 Science90.5%Expert-Level—Factual Recall33.7%

Math

Competition Math94.7%

Coding

Real-World Coding—

Agentic

Terminal Tasks—Novel Reasoning—

Reasoning

AgenticInsufficient data

ReasoningInsufficient data

MathInsufficient data

Sources:ProviderOpenRouter

Cheaper61%

Capability

Capability—

Reasoning & Knowledge

Graduate Science—Expert-Level—Factual Recall—

Math

Competition Math—

Coding

Real-World Coding70.8%

Agentic

Terminal Tasks—Novel Reasoning—

Reasoning

CodingInsufficient data

Sources:Epoch AIProviderOpenRouter

Capability

Capability—

Reasoning & Knowledge

Graduate Science3%93.5%Expert-Level43.5%Factual Recall50%50.6%

Math

Competition Math3%97.2%

Coding

Real-World Coding—

Agentic

Terminal Tasks88.3%Novel Reasoning60.4%

Specs

Context

128K

Max output

Jun 2026

Released

256K

Context

128K

Max output

May 2026

Released

1.0M

Context

256K

Max output

Jul 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$1.00/M tokens

Output80%$2.00/M tokens

Cache read$0.20/M tokens

Web search50%$0.005/search

Live pricing, shown before you run

Input70%$0.30/M tokens

Output$11.94/M tokens

Cache read$0.21/M tokens

Chat with Claude Sonnet 5 Go to model

Chat with Grok Build 0.1 Go to model

Chat with Kimi K3 Go to model

Frequently asked

Which of Claude Sonnet 5, Grok Build 0.1, and Kimi K3 is the cheapest?

Grok Build 0.1 has the lowest blended list price. Per 1M tokens: Claude Sonnet 5 at $2.00 in / $10.00 out; Grok Build 0.1 at $1.00 in / $2.00 out; Kimi K3 at $0.30 in / $11.94 out.

Which of Claude Sonnet 5, Grok Build 0.1, and Kimi K3 has the largest context window?

Kimi K3 leads with 1M tokens. The other two: Claude Sonnet 5 at 1M, Grok Build 0.1 at 256K.

Do Claude Sonnet 5, Grok Build 0.1, and Kimi K3 support image input?

Yes, all three accept images.

Where can I run Claude Sonnet 5, Grok Build 0.1, and Kimi K3 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 6 Astra vs Claude Opus 5 vs Gemini 3.1 Pro Claude Fable 5.1 vs GPT 6 Astra vs Grok 4.6 GPT 5.6 Luna vs Gemini 3.8 Flash vs Claude Haiku 4.5 Claude Sonnet 5 vs Kimi K2.7 Code vs Qwen3 Coder Next DeepSeek V4 Pro (0813) vs Qwen3.8 2.4T A95B vs Nemotron 3 Ultra GLM 5.3 Flash vs MiniMax M3 vs DeepSeek V4 Flash Muse Spark 1.3 vs Kimi K3 vs Grok 4.6 DeepSeek V4 Flash vs Gemini 3.8 Flash vs Qwen3.7 Plus GLM 5.3 vs MiniMax M3 vs DeepSeek V4 Pro (0813)