PulseAugur
中
实时 06:39:31
English(EN) We ran DeepSeek Harness against Kimchi on the same model. It lost by 22 points

Kimchi AI 代理在基准测试中以 22 分的优势超越 DeepSeek Harness

在 GLM 5.3 Flash 模型上进行的基准测试对比中,AI 编码代理 Kimchi 的表现比 DeepSeek Harness 高出 22.3 个百分点。由 Kimchi 的创建者 Matas Kaminskas 进行的测试旨在对比 Harness 框架本身,而非底层模型。在 DeepSeek Harness 的三个预设配置下,通过率范围为 44.0% 至 47.1%,而 Kimchi 的通过率为 69.4%。这一发现表明,代理的框架对性能有显著影响,这在之前的对比中也观察到了这种模式。 AI

影响 强调了代理框架设计对 AI 性能的显著影响,表明 Harness 的效率是任务完成率的关键因素。

排序理由 使用基准测试对比 AI 代理 Harness 性能。[lever_c_demoted from research: ic=1 ai=1.0]

在 dev.to — LLM tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Kimchi AI 代理在基准测试中以 22 分的优势超越 DeepSeek Harness

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
使用基准测试对比 AI 代理 Harness 性能。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
3 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Kimchi ·

    我们用同一模型运行了 DeepSeek Harness 对比 Kimchi。DeepSeek Harness 落后 22 分

    <p><em>Originally published on the <a href="https://kimchi.dev/blog/deepseek-harness-vs-kimchi-terminal-bench" rel="noopener noreferrer">Kimchi blog</a> by Matas Kaminskas.</em></p> <p>DeepSeek Harness (dsh) came out on August 13, 2026. Seven weeks later it has 239,003 GitHub sta…