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估算
50
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
基准测试分数 (LLM Stats)
Agents
WideSearch
79.0%自报
DeepSearchQA
77.1%自报
BrowseComp
74.9%自报
PaperBench
63.5%自报
Terminal-Bench 2.0
50.8%自报
SWE-Bench Pro
50.7%自报
CyberGym
41.3%自报
FrontierSWE
26.0%自报
Biology
GPQA
87.6%自报
SciCode
48.7%自报
Code
SWE-Bench Verified
76.8%自报
SWE-bench Multilingual
73.0%自报
OJBench (C++)
57.4%自报
Economics
FinSearchComp T2&T3
67.8%自报
Finance
MMLU-Pro
87.1%自报
General
LiveCodeBench v6
85.0%自报
MMMU-Pro
78.5%自报
SimpleVQA
0.71 / 100自报
LiveBench
69.1%自报
LongBench v2
61.0%自报
Healthcare
VideoMMMU
86.6%自报
Image To Text
OCRBench
92.3%自报
Long Context
LongVideoBench
79.8%自报
LVBench
75.9%自报
AA-LCR
70.0%自报
Math
AIME 2025
96.1%自报
HMMT 2025
95.4%自报
MathVista-Mini
90.1%自报
MathVision
84.2%自报
IMO-AnswerBench
81.8%自报
Humanity's Last Exam
50.2%自报
Multimodal
InfoVQAtest
92.6%自报
OmniDocBench 1.5
88.8%自报
Video-MME
87.4%自报
MMVU
80.4%自报
CharXiv-R
77.5%自报
MotionBench
70.4%自报
WorldVQA
46.3%自报
ZEROBench
0.11 / 100自报
Reasoning
Seal-0
57.4%自报
AA 评测指数
Intelligence Index29.4
Tau20.8
Gpqa0.8
Lcr0.6
Ifbench0.4
Scicode0.4
Terminalbench Hard0.2
Hle0.1
LLM Stats 分类评分
Language90
Legal90
Finance90
Image To Text80
Long Context80
Math80
Multimodal80
Frontend Development80
Video80
Vision80
Physics70
Reasoning70
Search70
Structured Output70
General70
Healthcare70
Biology70
Chemistry70
Agents60
Code50
Tool Calling50
Safety40
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$0.1 / 1M tokens
速度
Tokens/秒37.8
首Token延迟1.25s
首回答延迟1.25s
供应商价格排行
供应商价格排行
17 个供应商
最便宜: NanoGPT最贵: Moonshot AI
供应商输入输出
1NanoGPT最便宜
$0.3
$1.9
2CrofAI
$0.35
$1.7
3DigitalOcean
$0.5
$2.7
4Auriko
$0.5
$2.8
5Cortecs
$0.55
$2.76
6Alibaba (China)
$0.574
$2.411
7Kimi主要
$0.6
$3
8Abacus
$0.6
$3
9OpenCode Go
$0.6
$3
10OpenCode Zen
$0.6
$3
11FrogBot
$0.6
$3
12AIHubMix
$0.6
$3
13Moonshot AI (China)
$0.6
$3
14Azure Cognitive Services
$0.6
$3
15LLM Gateway
$0.6
$3
16Azure
$0.6
$3
17Moonshot AI
$0.6
$3
比较该模型在不同 API 供应商之间的定价。