跳转到主要内容

Kimi K2.6 (Non-reasoning)

KimiKimi开源权重Modified MIT License

描述

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.

发布日期
2026-04-20
参数规模
1.0T
上下文长度
262K
支持模态
image, text, video

能力雷达图

31
general
40
coding
79
reasoning
53
science估算
60
agents
80
multimodal

Science 在缺少专门科学评测时使用推理能力代理估算。

排行榜排名

领域#排名分数来源
智能体能力模型榜36
60.0
LS
代码能力榜94
68.0
AA
通用能力榜99
64.0
AA
多模态榜24
84.0
LS
推理能力66
61.0
LS
科学能力111
60.0
AA

基准测试分数 (LLM Stats)

Agents

GDPval-AA1202.00 / 3000自报
BrowseComp86.3%自报
DeepSearchQA83.0%自报
Claw-Eval80.9%自报
WideSearch80.8%自报
OSWorld-Verified73.1%自报
Terminal-Bench 2.066.7%自报
SWE-Bench Pro58.6%自报
MCP-Mark55.9%自报
Toolathlon50.0%自报
Finance Agent v244.9%自报
APEX-Agents27.9%自报
FrontierSWE27.0%自报

Biology

GPQA90.5%自报
SciCode52.2%自报

Code

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

General

LiveCodeBench v689.6%自报
MMMU-Pro80.1%自报
LiveBench72.2%自报

Math

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

Multimodal

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

Reasoning

OJBench60.6%自报

AA 评测指数

Intelligence Index
34.6
Tau2
0.9
Gpqa
0.8
Lcr
0.6
Ifbench
0.4
Scicode
0.4
Terminalbench Hard
0.4
Hle
0.2

LLM Stats 分类评分

Legal
100
Finance
100
General
100
Agents
93
Reasoning
51
Math
80
Multimodal
80
Search
80
Frontend Development
80
Coding
80
Vision
80
Physics
70
Biology
70
Chemistry
70
Code
60
Tool Calling
60

定价

输入价格$0.95 / 1M tokens
输出价格$4 / 1M tokens
混合价格(3:1)$1.712 / 1M tokens
缓存读取价格$0.16 / 1M tokens

速度

Tokens/秒63.9
首Token延迟1.18s
首回答延迟1.18s

供应商价格排行

供应商价格排行

16 个供应商

最便宜: Fireworks最贵: Auriko
供应商输入输出
1Fireworks最便宜
$0
$0
2Moonshot AI
$0
$0
3Novita
$0
$0
4CrofAI
$0.5
$1.99
5Cortecs
$0.81
$3.54
6Alibaba (China)
$0.929
$3.858
7Kimi主要
$0.95
$4
8OpenCode Go
$0.95
$4
9OpenCode Zen
$0.95
$4
10AIHubMix
$0.95
$4
11Moonshot AI (China)
$0.95
$4
12Azure Cognitive Services
$0.95
$4
13DigitalOcean
$0.95
$4
14LLM Gateway
$0.95
$4
15Azure
$0.95
$4
16Auriko
$0.95
$4

比较该模型在不同 API 供应商之间的定价。

外部链接