ratelimit now
Get updates

Kimi K3

By Moonshot. 8 results on 8 boards, copied as published. Different boards, different metrics: don't add them up.

License (as listed)Kimi K3 license
Hosting regionNot confirmed
Boards8
Code
  • 93.4%Vals AI — SWE-bench Verified

    Kimi K3 · % resolved · board #8

    Mini-SWE-agent · as of 2026-09-01 Stale ↗

  • 87.19%Vals AI — LiveCodeBench

    Kimi K3 · Accuracy % · board #18

    Vals AI implementation (no agent) · as of 2026-09-01 Stale ↗

Agentic / terminal

No result on the boards we captured

Websites
  • 1655LMArena WebDev Arena

    Kimi K3 (Max) · Arena score · board #17

    LMArena WebDev (agentic front-end tasks) · as of 2026-10-22 ↗

  • 84.97%Vals AI Vibe Code Bench v1.1

    Kimi K3 · Score % · board #16

    OpenHands · as of 2026-10-20 ↗

  • 1315Design Arena (Fullstack)

    kimi-k3 · Elo · board #3

    Design Arena · as of 2026-10-24 ↗

Design
  • 1359Design Arena (All categories)

    kimi-k3 · Elo · board #5

    Design Arena · as of 2026-10-24 ↗

Android
  • 90.2%Android Bench 1.0 tasks (100 tasks)

    Kimi K3 · Score %

    not_stated · as of 2026-08-11 ↗

  • 12%Android Bench 2.0 (long-horizon, 30 tasks)

    Kimi K3 · Pass rate

    kimi-code · as of 2026-10-06 ↗

iOS

No mature public leaderboard

Available in

Amazon Kiro Pro Amazon Kiro Pro+ Amazon Kiro Pro Max Amazon Kiro Power

Plans whose row in our pricing data names this model.

Use cases with this model

GPT-6 AstraClaude Opus 5.5Kimi K3

MotionPromptGallery: "178 AI motion graphics … made with Opus 5.5, GPT-6 Astra, Kimi K3, Fable 5", Next.js on Vercel

Builder
@mikenevermiss
Posted
Plan
—
Cost
Not disclosed
WebsitesDesignRead the post

x.com · link re-checked 2026-10-16

ClineKimi K3

Cline + Kimi K3 evaluated in production and on Terminal-Bench 2.1 (pass rate 77.5% to 88.8%)

Builder
Jangwook Kim
Posted
Plan
BYO key; mentions ClinePass "$9.99/month"
Cost
Stated: Kimi K3 baseline cost $79 for 89 attempts
CodeRead the post

dev.to · web source · link re-checked 2026-10-16

Kimi K3GLM-5.3Qwen 3.8 Max+2Model test

Test: "Qwen 3.8 Max (max): 25.7 - DeepSeek V4.1 Flash (max): 21.7 - Kimi K3 (default): 23 - GLM-5.3 (max): 19 - Mistral Large 4 (high, its max): 15"

Builder
@PawelHuryn
Posted
Plan
—
Cost
Not disclosed
CodeRead the post

x.com · link re-checked 2026-10-16

Kimi K3GLM 5.3Model test

"benchmarked worse + similar price as Kimi K3 and GLM 5.3 in the Pi harness", run on real PRs

Builder
@avyvar
Posted
Plan
—
Cost
Not disclosed
CodeRead the post

x.com · link re-checked 2026-10-16

Kimi K3GLM 5.3Qwen3.8 Max 0902+1Vendor post

Self-playing Flappy Bird and Missile Command games, each one-shot in a single HTML file, comparing 4 open models

Builder
EmpirioLabs AI
Posted
Plan
Run on the EmpirioLabs platform
Cost
Not disclosed
WebsitesDesignRead the post

empiriolabs.ai · web source · link re-checked 2026-10-16

Claude Opus 5.5Kimi K3Vendor post

Two models each built Pokémon Emerald "worms" (security research); compared bugs found

Builder
Kiwi Issa
Posted
Plan
Kimi K3, Opus 5.5
Cost
Not disclosed
CodeRead the post

runsybil.com · web source · link re-checked 2026-10-16

GPT-6 AstraClaude Opus 5.5Kimi K3Model test

Cost (test): "Opus 5.5: $8.95 | 10 mins GPT-6 Astra: $7.45 | 8 mins GPT-6 Sol: $3.90 | 5 mins Kimi K3: $4.04 | 6 mins" (Eiffel Tower in three.js)

Builder
@Bhavani_00007
Posted
Plan
—
Cost
Not disclosed
DesignRead the post

x.com · link re-checked 2026-10-16

Kimi K3

A fraud-detection pipeline: "Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3 … 96/100 correct for only ~$0.07"

Builder
@nutlope
Posted
Plan
—
Cost
Not disclosed
CodeRead the post

x.com · link re-checked 2026-10-16

GPT-6 AstraKimi K3

Chess game pitting GPT-6 Astra vs Kimi K3 via API ("Kimi K3 … beat it")

Builder
@Bhavani_00007
Posted
Plan
—
Cost
Not disclosed
CodeRead the post

x.com · link re-checked 2026-10-16

Kimi K3

3D map of the LEAP 2026 exhibition "built … with Kimi K3"

Builder
@mansoordotai
Posted
Plan
—
Cost
Not disclosed
WebsitesDesignRead the post

x.com · link re-checked 2026-10-16

Kimi K3

Podcast player "With Claude & Kimi K3, in only a couple of days. Pure html + css + javascript"

Builder
@Vladcostea
Posted
Plan
—
Cost
Not disclosed
WebsitesRead the post

x.com · link re-checked 2026-10-16

Same family: Kimi 3

Kimi K2.7 CodeGLM-5.3 FlashGLM-5.3Self-promo

Mainbrella Build: a Lovable-style app builder running open models on Cloudflare Workers AI

Builder
Andrew Arrow
Posted
Plan
GLM-5.3 / Kimi K2.7 Code
Cost
Not disclosed
CodeRead the post

mainbrella.com · web source · link re-checked 2026-10-16

Kimi family

Kimi Code skills: voice-to-video, audio input

Builder
@your_javaguy
Posted
Plan
—
Cost
Not disclosed
CodeRead the post

x.com · link re-checked 2026-10-16

Kimi familyModel test

Test: a robotic hummingbird in three.js; "MiMo-v2.6 Flash is 94% cheaper than Kimi-K3 here"

Builder
@TimJayas
Posted
Plan
—
Cost
Not disclosed
DesignRead the post

x.com · link re-checked 2026-10-16

Sources

lmarena.ai/leaderboard/webdev vals.ai/benchmarks/vibe-code vals.ai/benchmarks/swebench vals.ai/benchmarks/lcb developer.android.com/bench designarena.ai/leaderboard designarena.ai/leaderboard/fullstack

The weekly diff

What changed in AI coding plans: prices, limits, resets. Email signups open soon. Until then, updates go out on X.

Follow @QuietlyByG on X RSS feed

No email form yet, so we don't collect any email addresses.