跳轉到主要內容

Kimi K2.6 (Non-reasoning)

KimiKimi開源權重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.

發布日期
2026-04-20
參數規模
1.0T
上下文長度
262K
支援模態
image, text, video

能力雷達圖

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

Science 在缺少專門科學評測時使用推理能力代理估算。

排行榜排名

領域#排名分數來源
智慧體能力模型榜36
60.0
LS
程式碼能力榜94
68.0
AA
通用能力榜99
64.0
AA
多模態榜24
84.0
LS
推理能力66
61.0
LS
科學能力111
60.0
AA

基準測試分數 (LLM Stats)

Agents

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

Biology

GPQA90.5%自報
SciCode52.2%自報

Code

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

General

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

Math

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

Multimodal

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

Reasoning

OJBench60.6%自報

AA 評測指數

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 分類評分

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

定價

輸入價格$0.95 / 1M tokens
輸出價格$4 / 1M tokens
混合價格(3:1)$1.712 / 1M tokens
快取讀取價格$0.16 / 1M tokens

速度

Tokens/秒63.9
首Token延遲1.18s
首回答延遲1.18s

供應商價格排行

供應商價格排行

16 個供應商

最便宜: Fireworks最貴: Auriko
供應商輸入輸出
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

比較該模型在不同 API 供應商之間的定價。

外部連結