whatmodel.sh / Kimi K2.7 Code

Kimi K2.7 Code

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Kimi K2.7 Code is an open-weights language model from Moonshot AI, released June 2026. Its published size is 1000B parameters (32B active per token) and a 262k-token context window. Licence: modified-mit.

Catalogue identity notes

Comparison-only. Model card (moonshotai/Kimi-K2.7-Code @74797c9): MoE, Total Parameters 1T, Activated Parameters 32B; weights under the Modified MIT License. Epoch model_metadata.csv: 2026-06-12, 'Open weights (unrestricted)'. Arena entry 'kimi-k2.7-code' (moonshot, Modified MIT).

72.1±1.0#67 of 719 LLMsfrom 7 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Kimi K2.7 Code, out of 828 with a score, then more from Moonshot AI.

#modelscorewhereRAMreleased
70Claude Opus 4.5 Anthropic72±1api $10.00/M2025-11
71Qwen3.7 Plus Alibaba72±1api $0.70/M2026-06
72Kimi K2.7 Code Moonshot AI72±1api $1.71/M +local~359GB2026-06
73DeepSeek V4 Flash (Preview, Apr 2026) DeepSeek72±1local~103GB2026-04
74Grok 4.20 (0309 reasoning) SpaceXAI (xAI)72±1api $1.56/M2026-04
more from Moonshot AI
25Kimi K3 Moonshot AI77±1api $6.00/M +local~884GB2026-07
61Kimi K2.6 Moonshot AI73±1api $1.71/M +local~317GB2026-04
92Kimi K2.5 Moonshot AI70±1api $1.20/M +local~160GB2026-01

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #57 of 458 * · 15% of its score · 1 test

Beats GPT-5.4, DeepSeek V4 Flash Vision (Exp), Gemini 3.1 Pro (Preview) here, though they rank higher overall. Trails MiniMax-M3, GLM-5.1, Mistral Large 4 (public preview) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena WebDev (Code Arena)1472.9 ✎▁▂▄▃▅█▄▇▆▄▁▁ beats 64/119avg 981▇▇▇▇▇▇ 15%sharp
math▁▂▃▅▆▅▄█▄▁▁▁ #51 of 398 · 67% of its score · 3 tests

Beats LongCat 2.0 (1.6T-A48B), Qwen3.6 Max Preview, Claude Sonnet 4.6 here, though they rank higher overall. Trails A.X K2 (688B-A33B), DeepSeek V4 Flash (Preview, Apr 2026) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
FrontierMath tiers 1–3 v254.0% ✎▂··▁▁▃▄▄█▅▃▃ beats 38/82very hard · avg 1.2%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 42%sharp · at its level
FrontierMath tier 4 v212.2% ✎▁▂▁▃█▅▂▂▁▁▁▁ beats 12/63very hard · avg 0.1%▇▇▇▇▇▇▇▇▇ 23%sharp
OTIS mock AIME 2024–202595.6% ✎▃▃▄▃▃▃▇▇█▃▂▅ beats 162/193very hard · avg 8.5%▇ 2.8%sharp · noisy
other tests3 not in a task · 17% of its score
testresultvs the others in its rundifficultycountswhy
GPQA Diamond87.9% ✎▁▁▁▁▂▄▆▄▅▇█▅ beats 160/208hard · avg 40%▇▇▇ 8.6%sharp
Chess Puzzles (Epoch)21.0% ✎█▁▁▁▁▂▁▄▂▂▁▁ beats 84/135very hard · avg 5.9%▇▇ 5.6%sharp · noisy
SimpleQA Verified36.5% ✎▁▁▃▂▃▃▆▆█▃▂▅ beats 31/78very hard · avg 8.0%▇ 3.3%at its level

$ where to run it

Through an API

api · $1.71/M · $0.95 in / $4 out per 1M tokens · 262k context · platform.kimi.ai ↗ · price sourceUSD per 1M tokens, Kimi API (Moonshot AI) pay-as-you-go, kimi-k2.7-code: input (cache miss) $0.95, output $4.00; cache-hit input $0.19 and kimi-k2.7-code-highspeed ($1.90/$8.00) excluded; taxes excluded. Currency: USD. Moonshot AI Kimi official pricing page, observed 2026-09-25.

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run Kimi K2.7 Code · needs ~584.66 GB · from huggingface.co/unsloth
    chat in the terminal
    llama cli -hf unsloth/Kimi-K2.7-Code-GGUF:UD-Q4_K_XL
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf unsloth/Kimi-K2.7-Code-GGUF:UD-Q4_K_XL

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Kimi K2.7 Code · needs ~584.66 GB · from huggingface.co/unsloth

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/unsloth/Kimi-K2.7-Code-GGUF@UD-Q4_K_XL -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Official weights and documentation: huggingface.co/moonshotai ↗

$ how the score was worked out · Epoch AI — internal evaluatio… 85%, LMArena leaderboard dataset 15%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Epoch AI — internal evaluations6▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 85%CC BY 4.0
LMArena leaderboard dataset1▇▇▇▇ 15%CC BY 4.0
prior · pull toward the middle▇ 0%
weighted average= 72.1

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json