DeepSeek-V4.1-FlashvsDeepSeek-V4-Flash
在 12 个共同 benchmark 中，DeepSeek-V4.1-Flash 整体领先：DeepSeek-V4.1-Flash 领先 12 项，DeepSeek-V4-Flash 领先 0 项，持平 0 项，平均分差 +29.58。
DeepSeek-V4.1-Flash
DeepSeek-AI · 2026-09-10 · 多模态大模型
DeepSeek-V4-Flash
DeepSeek-AI · 2026-04-24 · 推理大模型
DeepSeek-V4.1-Flash12 项(100%)(0%)0 项DeepSeek-V4-Flash
评测分数
按能力类目分组，每组内按分差大小排列；共 12 项。
AI Agent - Tool Usage
DeepSeek-V4.1-Flash 领先 4/4| 评测项 | DeepSeek-V4.1-Flash | DeepSeek-V4-Flash | 分差 |
|---|---|---|---|
| Terminal-Bench 4.0 | 31.207 / 16Max (With Tools) | 716 / 16Max (With Tools) | +24.20 |
| Terminal-Bench 3.0 | 304 / 11Max (With Tools) | 7.6011 / 11Max (With Tools) | +22.40 |
| CyberGym | 88.101 / 8Max (With Tools) | 76.707 / 8Max (With Tools) | +11.40 |
| Terminal-Bench 2.1 | 90.601 / 53Max (With Tools) | 82.7024 / 53Max (With Tools) | +7.90 |
Coding and Software Engineer
DeepSeek-V4.1-Flash 领先 4/4| 评测项 | DeepSeek-V4.1-Flash | DeepSeek-V4-Flash | 分差 |
|---|---|---|---|
| CodeForces | 3,4711 / 21Max (No Tools) | 3,2893 / 21Max (No Tools) | +182 |
| SEC-Bench Pro | 62.804 / 5Max (With Tools) | 30.905 / 5Max (With Tools) | +31.90 |
| DeepSWE | 74.202 / 38Max (With Tools) | 54.4026 / 38Max (With Tools) | +19.80 |
| NL2Repo-Bench | 65.402 / 16Max (With Tools) | 54.2012 / 16Max (With Tools) | +11.20 |
Agent Level Benchmark
DeepSeek-V4.1-Flash 领先 1/1| 评测项 | DeepSeek-V4.1-Flash | DeepSeek-V4-Flash | 分差 |
|---|---|---|---|
| Agents' Last Exam | 31.806 / 19Max (With Tools) | 25.2016 / 19Max (With Tools) | +6.60 |
Math and Reasoning
DeepSeek-V4.1-Flash 领先 1/1| 评测项 | DeepSeek-V4.1-Flash | DeepSeek-V4-Flash | 分差 |
|---|---|---|---|
| MathArena Apex | 65.601 / 3Max (No Tools) | 58.603 / 3Max (No Tools) | +7 |
Productivity Knowledge
DeepSeek-V4.1-Flash 领先 1/1| 评测项 | DeepSeek-V4.1-Flash | DeepSeek-V4-Flash | 分差 |
|---|---|---|---|
| AutomationBench | 54.801 / 17Max (With Tools) | 37.7010 / 17Max (With Tools) | +17.10 |
智能体
DeepSeek-V4.1-Flash 领先 1/1| 评测项 | DeepSeek-V4.1-Flash | DeepSeek-V4-Flash | 分差 |
|---|---|---|---|
| ExploitGym (budget unspecified) | 15.302 / 4Max (With Tools) | 1.804 / 4Max (With Tools) | +13.50 |
规格对比
| 字段 | DeepSeek-V4.1-Flash | DeepSeek-V4-Flash |
|---|---|---|
| 发布机构 | DeepSeek-AI | DeepSeek-AI |
| 发布时间 | 2026-09-10 | 2026-04-24 |
| 模型类型 | 多模态大模型 | 推理大模型 |
| 架构 | MoE 架构 | MoE 架构 |
| 参数规模 | 5520亿 | 2840亿 |
| 上下文长度 | 1M | 1M |
| 最大输出 | 384K | 384K |
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-V4.1-Flash | DeepSeek-V4-Flash |
|---|---|---|
| 文本输入 | ¥1 / 1M tokens | $0.14 / 1M tokens |
| 文本输出 | ¥4 / 1M tokens | $0.28 / 1M tokens |
| 缓存读取 | ¥0.02 / 1M tokens | $0.0028 / 1M tokens |
小结
- DeepSeek-V4.1-Flash在以下类目领先:AI Agent - Tool Usage (4/4)、Coding and Software Engineer (4/4)、Agent Level Benchmark (1/1)、Math and Reasoning (1/1)、Productivity Knowledge (1/1)、智能体 (1/1)
12 个共同 benchmark 上，DeepSeek-V4.1-Flash 平均高出 29.58 分。
单项差距最大的 benchmark：CodeForces — DeepSeek-V4.1-Flash 3,471，DeepSeek-V4-Flash 3,289（分差 +182）。
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。