Kimi K3
Kimi · 2 thinking configurations
Intelligence34.5
Input / 1M$3.00
Output / 1M$15.00
Context1M
Tariff: Kimi · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 1 without both values
Selected: thinking low · Click a point to switch configuration
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
34.5 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
84.2 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
25.0 %SciCodeCode generation for scientific research problems.
52.7 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
82.4 %MMMU-ProMultimodal understanding of academic problems that include images.
78.5 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
45.8 %Specifications from the catalog
Inputtext, image, video
Outputtext
Tool callingYes
Structured outputYes
Speed38.2 tok/s
First token5.66 s
Maximum output943.7K
Catalog listing date2026-07-16