DataLearner 标志

DeepSeek-V4-ProvsKimi K2.6

在 10 个共同 benchmark 中,Kimi K2.6 整体领先:DeepSeek-V4-Pro 领先 2 项,Kimi K2.6 领先 8 项,持平 0 项,平均分差 -17.34。

DeepSeek-AI
DeepSeek-V4-Pro

DeepSeek-AI · 2026-04-24 · 推理大模型

Moonshot AI
Kimi K2.6

Moonshot AI · 2026-04-20 · 推理大模型

DeepSeek-V4-Pro2 (20%)(80%)8 Kimi K2.6

评测分数

按能力类目分组,每组内按分差大小排列;共 10 项。

Coding and Software Engineer

Kimi K2.6 领先 4/4
评测项DeepSeek-V4-ProKimi K2.6分差
LiveCodeBench56.8076 / 123Normal (No Tools)89.607 / 123Thinking (No Tools)-32.80
SWE-bench Multilingual69.8018 / 23Normal (With Tools)76.705 / 23Thinking (With Tools)-6.90
SWE-bench Verified73.6045 / 112Normal (With Tools)80.2014 / 112Thinking (With Tools)-6.60
SWE-Bench Pro - Public52.1038 / 54Normal (With Tools)58.6013 / 54Thinking (With Tools)-6.50

General Knowledge

Kimi K2.6 领先 2/3
评测项DeepSeek-V4-ProKimi K2.6分差
HLE7.70156 / 172Normal (No Tools)5415 / 172Thinking (With Tools + Internet)-46.30
GPQA Diamond72.90108 / 187Normal (No Tools)90.5018 / 187Thinking (No Tools)-17.60
LiveBench73.5823 / 115Normal (No Tools)72.1728 / 115Thinking (No Tools)+1.41

AI Agent - Information Search

DeepSeek-V4-Pro 领先 1/1
评测项DeepSeek-V4-ProKimi K2.6分差
BrowseComp83.4013 / 53极高强度思考(工具)83.2014 / 53Thinking (With Tools + Internet)+0.20

AI Agent - Tool Usage

Kimi K2.6 领先 1/1
评测项DeepSeek-V4-ProKimi K2.6分差
Terminal Bench 2.059.1022 / 47Normal (With Tools)66.7010 / 47Thinking (With Tools)-7.60

Math and Reasoning

Kimi K2.6 领先 1/1
评测项DeepSeek-V4-ProKimi K2.6分差
IMO-AnswerBench35.3021 / 21Normal (No Tools)868 / 21Thinking (No Tools)-50.70

规格对比

字段DeepSeek-V4-ProKimi K2.6
发布机构DeepSeek-AIMoonshot AI
发布时间2026-04-242026-04-20
模型类型推理大模型推理大模型
架构MoE 架构MoE 架构
参数规模1.6万亿1万亿
上下文长度1M256K
最大输出375K暂无数据

API 调用价格

价格优先使用 DataLearner 配置的 API 记录;缺失项不做推测。

价格项DeepSeek-V4-ProKimi K2.6
文本输入$0.435 / 1M tokens$0.95 / 1M tokens
文本输出$0.87 / 1M tokens$4 / 1M tokens
缓存读取$0.87 / 1M tokens$0.16 / 1M tokens
缓存写入$0.003625 / 1M tokens$0.95 / 1M tokens

小结

  • DeepSeek-V4-Pro在以下类目领先:AI Agent - Information Search (1/1)
  • Kimi K2.6在以下类目领先:Coding and Software Engineer (4/4)、General Knowledge (2/3)、AI Agent - Tool Usage (1/1)、Math and Reasoning (1/1)

10 个共同 benchmark 上,Kimi K2.6 平均高出 17.34 分。

单项差距最大的 benchmark:IMO-AnswerBench — DeepSeek-V4-Pro 35.30,Kimi K2.6 86(分差 -50.70)。

本页正文由结构化模型、价格与 benchmark 数据生成,不使用实时 LLM 撰写。