From 204c68d47506d1f7816f5bde215bb234701043f1 Mon Sep 17 00:00:00 2001 From: "Paul Gauthier (aider)" Date: Tue, 28 Jan 2025 09:51:26 -0800 Subject: [PATCH] feat: Add blog post template for DeepSeek V3 polyglot benchmark results --- .../_posts/2025-01-28-deepseek-down.md | 73 +++++++++++++++++++ 1 file changed, 73 insertions(+) diff --git a/aider/website/_posts/2025-01-28-deepseek-down.md b/aider/website/_posts/2025-01-28-deepseek-down.md index e69de29bb..5c7fd28c5 100644 --- a/aider/website/_posts/2025-01-28-deepseek-down.md +++ b/aider/website/_posts/2025-01-28-deepseek-down.md @@ -0,0 +1,73 @@ +--- +title: DeepSeek V3 polyglot benchmark results by provider +excerpt: Comparing DeepSeek V3 performance across different providers on aider's polyglot benchmark. +highlight_image: /assets/deepseek-down.jpg +draft: false +nav_exclude: true +--- +{% if page.date %} +

{{ page.date | date: "%B %d, %Y" }}

+{% endif %} + +# DeepSeek V3 polyglot benchmark results by provider +{: .no_toc } + + + +DeepSeek V3 is a powerful open source model that performs well on aider's polyglot benchmark. +However, the results can vary significantly depending on which provider is serving the model. + +This article compares DeepSeek V3 results from multiple providers to help you choose the best option for your needs. + +## Results + + + + + + + + + + + + + + {% assign edit_sorted = site.data.deepseek-down | sort: 'pass_rate_2' | reverse %} + {% for row in edit_sorted %} + + + + + + + + + {% endfor %} + +
ModelPercent completed correctlyPercent using correct edit formatCommandEdit formatTotal Cost
{{ row.model }}{{ row.pass_rate_2 }}%{{ row.percent_cases_well_formed }}%{{ row.command }}{{ row.edit_format }}{% if row.total_cost == 0 %}?{% else %}${{ row.total_cost | times: 1.0 | round: 2 }}{% endif %}
+ + + + +