Kimi K2.6vsKimi K2.5
在 14 个共同 benchmark 中，Kimi K2.6 整体领先：Kimi K2.6 领先 11 项，Kimi K2.5 领先 3 项，持平 0 项，平均分差 +15.42。
Kimi K2.611 项(79%)(21%)3 项Kimi K2.5
评测分数
按能力类目分组，每组内按分差大小排列；共 14 项。
Coding and Software Engineer
Kimi K2.6 领先 3/3| 评测项 | Kimi K2.6 | Kimi K2.5 | 分差 |
|---|---|---|---|
| SWE-Bench Pro - Public | 58.6018 / 62Thinking (With Tools) | 50.7047 / 62Thinking (With Tools) | +7.90 |
| LiveCodeBench | 89.6011 / 250Thinking (No Tools) | 8529 / 250Thinking (No Tools) | +4.60 |
| SWE-bench Verified | 80.2014 / 116Thinking (With Tools) | 76.8030 / 116Thinking (With Tools) | +3.40 |
General Knowledge
Kimi K2.6 领先 2/2| 评测项 | Kimi K2.6 | Kimi K2.5 | 分差 |
|---|---|---|---|
| HLE | 19.60290 / 563Normal (No Tools) · Text only | 13.20357 / 563Normal (No Tools) · Text only | +6.40 |
| LiveBench | 70.5434 / 117Thinking (No Tools) | 69.0741 / 117Thinking (No Tools) | +1.47 |
Math and Reasoning
Kimi K2.6 领先 2/2| 评测项 | Kimi K2.6 | Kimi K2.5 | 分差 |
|---|---|---|---|
| IMO-AnswerBench | 8610 / 24Thinking (No Tools) | 81.8018 / 24Thinking (No Tools) | +4.20 |
| AIME 2026 | 96.409 / 29Thinking (No Tools) | 92.5021 / 29Thinking (No Tools) | +3.90 |
AI Agent - Information Search
Kimi K2.6 领先 1/1| 评测项 | Kimi K2.6 | Kimi K2.5 | 分差 |
|---|---|---|---|
| BrowseComp | 83.2016 / 57Thinking (With Tools + Internet) | 60.6038 / 57Thinking (With Tools + Internet) | +22.60 |
AI Agent - Tool Usage
Kimi K2.6 领先 1/1| 评测项 | Kimi K2.6 | Kimi K2.5 | 分差 |
|---|---|---|---|
| Terminal Bench 2.0 | 66.7010 / 48Thinking (With Tools) | 50.8035 / 48Thinking (With Tools) | +15.90 |
Claw-style Agent Evaluation
Kimi K2.5 领先 1/1| 评测项 | Kimi K2.6 | Kimi K2.5 | 分差 |
|---|---|---|---|
| Claw Bench | 80.9019 / 29Thinking (With Tools) | 81.7018 / 29Thinking (With Tools) | -0.80 |
Long Context
Kimi K2.6 领先 1/1| 评测项 | Kimi K2.6 | Kimi K2.5 | 分差 |
|---|---|---|---|
| AA-LCR | 69.70106 / 170Normal (No Tools) | 67.30113 / 170Normal (No Tools) | +2.40 |
Text Embedding
Kimi K2.5 领先 1/1| 评测项 | Kimi K2.6 | Kimi K2.5 | 分差 |
|---|---|---|---|
| Context Arena | 51.8886 / 126Normal (No Tools) | 53.3383 / 126Normal (No Tools) | -1.45 |
Writing and Creative Capabilities
Kimi K2.6 领先 1/1| 评测项 | Kimi K2.6 | Kimi K2.5 | 分差 |
|---|---|---|---|
| Creative Writing | 1,72125 / 106Normal (No Tools) | 1,57643 / 106Normal (No Tools) | +145.50 |
科学与综合推理
Kimi K2.5 领先 1/1| 评测项 | Kimi K2.6 | Kimi K2.5 | 分差 |
|---|---|---|---|
| GPQA Diamond | 78.80249 / 462Normal (No Tools) | 78.90248 / 462Normal (No Tools) | -0.10 |
规格对比
| 字段 | Kimi K2.6 | Kimi K2.5 |
|---|---|---|
| 发布机构 | Moonshot AI | Moonshot AI |
| 发布时间 | 2026-04-20 | 2026-01-27 |
| 模型类型 | 推理大模型 | 多模态大模型 |
| 架构 | MoE 架构 | MoE 架构 |
| 参数规模 | 1万亿 | 1万亿 |
| 上下文长度 | 256K | 256K |
| 最大输出 | 暂无数据 | 16K |
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 | Kimi K2.6 | Kimi K2.5 |
|---|---|---|
| 文本输入 | $0.95 / 1M tokens | $0.6 / 1M tokens |
| 文本输出 | $4 / 1M tokens | $3 / 1M tokens |
| 缓存读取 | $0.16 / 1M tokens | $0.1 / 1M tokens |
| 缓存写入 | $0.95 / 1M tokens | 暂无公开价格 |
小结
- Kimi K2.6在以下类目领先:Coding and Software Engineer (3/3)、General Knowledge (2/2)、Math and Reasoning (2/2)、AI Agent - Information Search (1/1)、AI Agent - Tool Usage (1/1)、Long Context (1/1)、Writing and Creative Capabilities (1/1)
- Kimi K2.5在以下类目领先:Claw-style Agent Evaluation (1/1)、Text Embedding (1/1)、科学与综合推理 (1/1)
14 个共同 benchmark 上，Kimi K2.6 平均高出 15.42 分。
单项差距最大的 benchmark：Creative Writing — Kimi K2.6 1,721，Kimi K2.5 1,576（分差 +145.50）。
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。