Kimi K2
Kimi · 1 configuration
Intelligence12.7
Input / 1M$0.57
Output / 1M$2.30
Context128K
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 · 0 without both values
Selected: thinking default · Click a point to switch configuration
Kimi model for long-context chat, coding, and agentic reasoning
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
12.7 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
76.6 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
7.4 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
61.1 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
41.5 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
27.4 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputNo
Speed53.3 tok/s
First token1.46 s
Maximum output64K
Catalog listing date2024-12-01