Kimi Linear 48B A3B Instruct
KimiKimi
发布日期
2025-10-30
参数规模
—
上下文长度
262K
支持模态
image, text, video
能力雷达图
23
general
34
coding
37
reasoning
26
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
Math Index36.3
Intelligence Index8.5
Mmlu Pro0.6
Gpqa0.4
Livecodebench0.4
Aime 250.4
Ifbench0.3
Lcr0.3
Scicode0.2
Terminalbench Hard0.1
Hle0.0
Tau20.0
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
输入价格免费
输出价格免费
混合价格(3:1)免费
缓存读取价格$0.1 / 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
暂无提供商数据