llmboard.aiLeaderboard Center
Overall
Overall RankingOpen Models
Tools
Model DirectoryCompare Models
Capabilities
CodingReasoningMathKnowledgeInstruction Following
Price & Efficiency
Price & ValueCapability vs. PriceRuntime Performance
Modalities
Image GenerationVideo GenerationSpeech ModelsEmbeddings
Core Benchmarks
GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-ProView all benchmarks
Methods
Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

Model vendor

Moonshot AI

Chinese AI company developing the Kimi series of large language models, including state-of-the-art mixture-of-experts models with long-context capabilities

Updated Aug 11, 2026. Data as of 2026-08-11

Website
Models8
Versions13
Open defaults5
CountryCN

On this page

  • Models
  • Scores
  • Highlights
  • About
  • FAQ

Moonshot AI models

Default-version specifications and scored-version capability values are labeled separately.

8 rows
Columns

Show columns

MAKimi K3Moonshot AIKimi K393.060.0%1MOpen weightsJul 16, 2026Kimi K3
MAKimi K2.6Moonshot AIKimi K2.675.580.0%262.1KOpen weightsApr 20, 2026Kimi K2.6
MAKimi K2.7 CodeMoonshot AIKimi K2.7 Code66.820.0%262.1KOpen weightsJun 12, 2026Kimi K2.7 Code
MAKimi K2.5Moonshot AIKimi K2.566.080.0%262.1KOpen weightsJan 27, 2026Kimi K2.5
MAKimi K2 ThinkingMoonshot AIKimi K2-Thinking-090561.0100.0%262.1KClosed weightsSep 5, 2025Kimi K2-Thinking-0905
MAKimi K2Moonshot AIKimi K2-Instruct-090537.2100.0%N/AClosed weightsSep 5, 2025Kimi K2-Instruct-0905
MAKimi k1.5Moonshot AIKimi-k1.530.160.0%N/AClosed weightsJan 20, 2025Kimi-k1.5
MAKimi K2 Thinking TurboMoonshot AIKimi K2 Thinking TurboN/AN/A262.1KOpen weightsNov 6, 2025Not scored

Moonshot AI capability scores

Each unique model uses its latest scored version.

Moonshot AI LLMBoard scores

Moonshot AI Highlights

Leading Moonshot AI models by score, price and context window.

Top scoreKimi K393.0 LLMBoardLowest official inputKimi K2.5$0.60 / 1MLargest contextKimi K31M tokens
Open-weight defaults5of 8 models

What is Moonshot AI?

Background and model catalog information for Moonshot AI.

Chinese AI company developing the Kimi series of large language models, including state-of-the-art mixture-of-experts models with long-context capabilities

Model ownership is separate from API hosting. One model can be offered by multiple API providers with different prices.

Vendor
Moonshot AI
Models
8
Versions
13
Country
CN
Founded
Not available

Catalog data as of 2026-08-11.

FAQ

Common questions about Moonshot AI.

What is Moonshot AI's highest-ranked model?

Kimi K3 currently has the strongest LLMBoard score from this vendor.

How many Moonshot AI models are tracked?

The catalog contains 8 independently selectable Moonshot AI models and 13 versions.

Does Moonshot AI host every listed model API?

Not necessarily. Vendor identifies the model developer; API providers are tracked separately.

Does Moonshot AI publish open-weight models?

5 current default versions are marked as open weight.