Kimi K2.6
Kimi · 2 thinking configurations
Intelligence27.0
Input / 1M$0.95
Output / 1M$4.00
Context256K
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 thinking · Click a point to switch configuration
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
27.0 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
91.1 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
37.5 %SciCodeCode generation for scientific research problems.
51.5 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
65.9 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
95.9 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
76.0 %MMMU-ProMultimodal understanding of academic problems that include images.
79.4 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
32.6 %Specifications from the catalog
Inputtext, image
Outputtext
Tool callingYes
Structured outputYes
Speed72.3 tok/s
First token2.82 s
Maximum output235.9K
Catalog listing date2026-04-20