跳转到主要内容

Kimi K2.5 (Non-reasoning)

KimiKimi开源权重MIT · 商用许可

描述

Kimi K2.5 is Moonshot AI's flagship agentic model and a new SOTA open model. It unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model. Built with Full-Parameter RL tuning, it achieves state-of-the-art performance across agents, coding, image, and video benchmarks.

发布日期
2026-01-27
参数规模
1.0T
上下文长度
262K
支持模态
image, text, video

能力雷达图

26
general
40
coding
79
reasoning
52
science
50
agents
80
multimodal

排行榜排名

领域#排名分数来源
智能体能力模型榜130
33.0
LS
代码能力榜205
54.0
AA
通用能力榜208
55.0
AA
多模态榜27
57.0
LS
科学能力194
56.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

WideSearch79.0%自报
DeepSearchQA77.1%自报
BrowseCompOpenAI (2025)74.9%自报
PaperBench63.5%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)50.8%自报
SWE-Bench ProPrinceton NLP (2024)50.7%自报
CyberGym41.3%自报
FrontierSWE26.0%

Biology

GPQANYU + Cohere + Anthropic (2023)87.6%自报
SciCode48.7%自报

Code

SWE-Bench Verified76.8%自报
SWE-bench Multilingual73.0%自报
OJBench (C++)57.4%自报

Economics

FinSearchComp T2&T367.8%自报

Finance

MMLU-Pro87.1%自报

General

LiveCodeBench v685.0%自报
MMMU-Pro78.5%自报
SimpleVQA0.71 / 100自报
LiveBench69.1%
LongBench v261.0%自报

Healthcare

VideoMMMU86.6%自报

Image To Text

OCRBench92.3%自报

Long Context

LongVideoBench79.8%自报
LVBench75.9%自报
AA-LCR70.0%自报

Math

AIME 202596.1%自报
HMMT 202595.4%自报
MathVista-Mini90.1%自报
MathVision84.2%自报
IMO-AnswerBench81.8%自报
Humanity's Last Exam50.2%自报

Multimodal

InfoVQAtest92.6%自报
OmniDocBench 1.588.8%自报
Video-MME87.4%自报
MMVU80.4%自报
CharXiv-R77.5%自报
MotionBench70.4%自报
WorldVQA46.3%自报
ZEROBench0.11 / 100自报

Reasoning

Seal-057.4%自报

AA 评测指数

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
30.1
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.8
Lcr(Artificial Analysis)
0.7
Ifbench(Google Research (2023))
0.4
Scicode(UIUC + Argonne National Lab (2024))
0.4
Terminalbench Hard(Stanford × Laude Institute (2026))
0.2
Hle(Center for AI Safety + Scale AI (2025))
0.1

LLM Stats 分类评分

(LLM Stats (zeroeval))
Legal
90
Language
90
Finance
90
Long Context
80
Math
80
Image To Text
80
Frontend Development
80
Video
80
Multimodal
70
Physics
70
Reasoning
70
Search
70
Structured Output
70
General
70
Healthcare
70
Biology
70
Chemistry
70
Vision
70
Agents
60
Code
50
Tool Calling
50
Safety
40

定价

输入价格$0.6 / 1M tokens
输出价格$3 / 1M tokens
混合价格(3:1)$1.2 / 1M tokens
缓存读取价格$0.095 / 1M tokens

速度

Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s

供应商价格排行

供应商价格排行

11 个供应商

最便宜: NanoGPT最贵: Ofox
供应商输入输出
1NanoGPT最便宜
$0.3
$1.9
2TensorX
$0.5
$2.8
3OpenRouter
$0.57
$2.85
4ZenMux
$0.58
$3.02
5Kimi主要
$0.6
$3
6Jiekou.AI
$0.6
$3
7NovitaAI
$0.6
$3
8Kilo Gateway
$0.6
$3
9Vercel AI Gateway
$0.6
$3
10HPC-AI
$0.6
$3
11Ofox
$0.6
$3

比较该模型在不同 API 供应商之间的定价。

外部链接