we’re getting used to it by now but DeepSeek calling this a “minor update” while moving Terminal-Ben...
TL;DR · AI 摘要
DeepSeek-V4.1-Flash-1017模型在Terminal-Bench 4.0和DeepSWE基准测试中表现显著提升，同时优化了任务完成速度和输出效率。
核心要点
- Terminal-Bench 4.0得分从31.2提升至42.3，性能提升35.5%
- DeepSWE基准测试得分为77.0，优于Opus 5和GPT-5.6 Sol
- 通过减少token使用量实现成本优化，MIT许可证开放权重
结构提纲
按章节快速跳转。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- DeepSeek-V4.1-Flash-1017更新
- 性能提升
- Terminal-Bench 4.0 42.3分
- DeepSWE 77.0分
- 成本优化
- 更短输出
- 更少token使用
- 开放性
- MIT许可证权重
金句 / Highlights
值得收藏与分享的关键句。
Terminal-Bench 4.0得分从31.2跃升至42.3，性能提升幅度达35.5%
DeepSWE基准测试中77.0得分优于Opus 5（74.0）和GPT-5.6 Sol（73.0）
通过减少token使用量实现成本优化，MIT许可证开放权重
Thomas Wolf on X: "we’re getting used to it by now but DeepSeek calling this a “minor update” while moving Terminal-Bench 4.0 from 31.2 to 42.3 is very funny. also reports 77.0 on DeepSWE (vs 74.0 for Opus 5 and 73.0 for GPT-5.6 Sol…) and the most interesting line may be faster task completion wi… / X
Thomas Wolf
@Thom_Wolf
we’re getting used to it by now but DeepSeek calling this a “minor update” while moving Terminal-Bench 4.0 from 31.2 to 42.3 is very funny. also reports 77.0 on DeepSWE (vs 74.0 for Opus 5 and 73.0 for GPT-5.6 Sol…) and the most interesting line may be faster task completion with shorter outputs. using fewer tokens is one of the practical way the cost curve collapses often done as an afterthought all with MIT-licensed weights in DeepSeek tradition now curious to see how these numbers will hold up outside their own eval setup
DeepSeek
@deepseek_ai
22h
🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for
@
DeepSeekHarness
, Tencent CodeBuddy,
Show more
10:17 AM · Oct 17, 2026
·
65.5K
Views
68
45
810
91