跳轉到主要內容

Kimi K2 Thinking

KimiKimi開源權重MIT · 商用許可

描述

Kimi K2 Thinking is the latest, most capable version of open-source thinking model. Starting with Kimi K2, it is built as a thinking agent that reasons step-by-step while dynamically invoking tools. It sets a new state-of-the-art on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks by dramatically scaling multi-step reasoning depth and maintaining stable tool-use across 200–300 sequential calls. At the same time, K2 Thinking is a native INT4 quantization model with 256k context window, achieving lossless reductions in inference latency and GPU memory usage. Key features include deep thinking & tool orchestration with end-to-end training to interleave chain-of-thought reasoning with function calls, native INT4 quantization via Quantization-Aware Training (QAT) achieving lossless 2x speed-up, and stable long-horizon agency maintaining coherent goal-directed behavior across up to 200–300 consecutive tool invocations.

發布日期
2025-11-06
參數規模
1.0T
上下文長度
262K
支援模態
text

能力雷達圖

70
general
50
coding
80
reasoning
51
science估算
50
agents
0
multimodal

缺少專門科學評測時,Science 由 LLM Stats 科學得分或推理能力估算。

排行榜排名

暫無排名資料

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Finance

FinSearchComp-T347.4%自報

Healthcare

HealthBench58.0%自報

Language

MMLU-Redux94.4%自報
MMLU-Pro84.6%自報

Math

AIME 2025100.0%自報
HMMT 202597.5%自報
IMO-AnswerBench78.6%自報

Reasoning

FRAMES87.0%自報
GPQANYU + Cohere + Anthropic (2023)84.5%自報
LiveCodeBench v683.1%自報
SWE-Bench Verified71.3%自報
BrowseComp-zh62.3%自報
SWE-bench Multilingual61.1%自報
BrowseCompOpenAI (2025)60.2%自報
Seal-056.3%自報
Humanity's Last Exam51.0%自報
OJBench48.7%自報
Terminal-Bench47.1%自報
SciCode44.8%自報
Multi-SWE-Bench41.9%自報

Writing

WritingBench73.8%自報

AA 評測指數

(Artificial Analysis)

暫無 AA 評測資料

LLM Stats 分類評分

(LLM Stats (zeroeval))
Language
90
Legal
80
Math
80
Finance
80
Reasoning
70
Search
70
Frontend Development
70
General
70
Healthcare
70
Communication
70
Creativity
70
Writing
70
Physics
60
Biology
60
Chemistry
60
Agents
50
Code
50
Vision
50

定價

輸入價格$0.6 / 1M tokens
輸出價格$2.5 / 1M tokens
混合價格(3:1)$1.075 / 1M tokens
快取讀取價格$0.15 / 1M tokens

速度

Tokens/秒122.3
首Token延遲1.53s
首回答延遲17.87s

供應商價格排行

供應商價格排行

11 個供應商

最便宜: OpenCode最貴: AI/ML API
供應商輸入輸出
1OpenCode最便宜
$0.4
$2.5
2Helicone
$0.48
$2
3Alibaba (China)
$0.574
$2.294
4302.AI
$0.575
$2.3
5Qiniu
$0.57971
$2.31884
6Kimi主要
$0.6
$2.5
7NanoGPT
$0.6
$2.5
8OpenRouter
$0.6
$2.5
9Novita AI
$0.6
$2.5
10Kilo Gateway
$0.6
$2.5
11AI/ML API
$0.6348
$2.645

比較該模型在不同 API 供應商之間的定價。

外部連結