Saltar al contenido principal

Kimi K2.6 (Non-reasoning)

KimiKimiOpen WeightModified MIT License

Descripción

Kimi K2.6 is Moonshot AI's open-source, native multimodal agentic model focused on state-of-the-art coding, long-horizon execution, and agent swarm capabilities. It scales horizontally to 300 sub-agents executing 4,000 coordinated steps, dynamically decomposing tasks into parallel, domain-specialized subtasks. K2.6 unifies text, image, and video input with thinking and non-thinking modes, supports a 256K context, and powers proactive 24/7 background agents that manage schedules, execute code, and orchestrate cross-platform operations without human oversight.

Fecha de lanzamiento
2026-04-20
Parámetros
1.0T
Longitud del contexto
262K
Modalidades
image, text, video

Radar de capacidades

38
general
39
coding
79
reasoning
53
scienceest.
60
agents
80
multimodal

Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.

Rankings

Dominio#PosiciónPuntuaciónFuente
Agents & Tools20
68.0
LS
Code Ranking69
67.0
AA
General Ranking88
70.0
AA
Multimodal Ranking22
84.0
LS
Reasoning62
61.0
LS
Science90
63.0
AA

Puntuaciones de benchmarks (LLM Stats)

Agents

BrowseComp86.3%Aut.
DeepSearchQA83.0%Aut.
Claw-Eval80.9%Aut.
WideSearch80.8%Aut.
OSWorld-Verified73.1%Aut.
Terminal-Bench 2.066.7%Aut.
SWE-Bench Pro58.6%Aut.
MCP-Mark55.9%Aut.
Toolathlon50.0%Aut.
APEX-Agents27.9%Aut.

Biology

GPQA90.5%Aut.
SciCode52.2%Aut.

Code

SWE-Bench Verified80.2%Aut.
SWE-bench Multilingual76.7%Aut.

General

LiveCodeBench v689.6%Aut.
MMMU-Pro80.1%Aut.

Math

AIME 202696.4%Aut.
MathVision93.2%Aut.
HMMT Feb 2692.7%Aut.
IMO-AnswerBench86.0%Aut.
Humanity's Last Exam36.4%Aut.

Multimodal

V*96.9%Aut.
CharXiv-R86.7%Aut.
BabyVision68.5%Aut.

Reasoning

OJBench60.6%Aut.

Índices de evaluación AA

Intelligence Index
43.0
Coding Index
38.4
Tau2
0.9
Gpqa
0.8
Lcr
0.6
Ifbench
0.4
Scicode
0.4
Terminalbench Hard
0.4
Hle
0.2

Puntuaciones por categoría LLM Stats

Vision
80
Coding
80
Frontend Development
80
General
80
Math
80
Multimodal
80
Reasoning
80
Search
80
Agents
70
Biology
70
Chemistry
70
Code
70
Physics
70
Tool Calling
60

Precios

Precio de entrada$0.95 / 1M tokens
Precio de salida$4 / 1M tokens
Precio mixto (3:1)$1.712 / 1M tokens

Velocidad

Tokens/seg28.5 tokens/s
Retraso del primer token1.71s
Tiempo hasta la respuesta1.71s

Proveedores disponibles

(Unidades internas LS)
ProveedorPrecio de entradaPrecio de salida
Novita950K4.0M
Moonshot AI950K4.0M

Fuentes externas