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

70
general
50
coding
80
reasoning
60
science估算
50
agents
80
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

领域#排名分数来源
多模态榜35
60.0
LS

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Code

PaperBench63.5%自报
CyberGym41.3%自报
FrontierSWE26.0%

Finance

FinSearchComp T2&T367.8%自报

Language

MMLU-Pro87.1%自报

Long Context

LongBench v261.0%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
LiveBench69.1%

Multimodal

Video-MME87.4%自报
VideoMMMU86.6%自报

Reasoning

GPQANYU + Cohere + Anthropic (2023)87.6%自报
LiveCodeBench v685.0%自报
CharXiv-R77.5%自报
SWE-Bench Verified76.8%自报
BrowseCompOpenAI (2025)74.9%自报
SWE-bench Multilingual73.0%自报
AA-LCR70.0%自报
OJBench (C++)57.4%自报
Seal-057.4%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)50.8%自报
SWE-Bench ProPrinceton NLP (2024)50.7%自报
Humanity's Last Exam50.2%自报
SciCode48.7%自报

Search

WideSearch79.0%自报
DeepSearchQA77.1%自报

Vision

InfoVQAtest92.6%自报
OCRBench92.3%自报
OmniDocBench 1.588.8%自报
MMVU80.4%自报
LongVideoBench79.8%自报
MMMU-Pro78.5%自报
LVBench75.9%自报
SimpleVQA0.71 / 100自报
MotionBench70.4%自报
WorldVQA46.3%自报
ZEROBench0.11 / 100自报

AA 评测指数

(Artificial Analysis)

暂无 AA 评测数据

LLM Stats 分类评分

(LLM Stats (zeroeval))
Language
90
Legal
90
Finance
90
Image To Text
80
Long Context
80
Math
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 / 1M tokens
缓存读取价格$0.15 / 1M tokens

速度

Tokens/秒54.0
首Token延迟2.26s
首回答延迟2.26s

供应商价格排行

供应商价格排行

11 个供应商

最便宜: OpenRouter最贵: HPC-AI
供应商输入输出
1OpenRouter最便宜
$0.5
$2.5
2TensorX
$0.5
$2.8
3IteraCompute
$0.54
$2.78
4NanoGPT
$0.557
$2.832
5Qiniu
$0.57971
$3.04348
6Kimi主要
$0.6
$3
7Jiekou.AI
$0.6
$3
8Novita AI
$0.6
$3
9Kilo Gateway
$0.6
$3
10Vercel AI Gateway
$0.6
$3
11HPC-AI
$0.6
$3

比较该模型在不同 API 供应商之间的定价。

外部链接