Tutorials & Tips

Cognition evaluates OpenAI o1 series on Devin coding agent and publishes evaluation method

Original title:A review of OpenAI’s o1 and how we evaluate coding agents

AI summary

Cognition published early results from weeks of testing o1-mini and o1-preview in Devin: on the internal cognition-golden benchmark, Devin-Base improved from 25.9% with GPT-4o to 34.6% with o1-mini and 51.8% with o1-preview, while production Devin reached 74.2%.

Key Takeaways

  • Cognition published early results from weeks of testing o1-mini and o1-preview in Devin: on the…
  • 9% with GPT-4o to 34.
  • 6% with o1-mini and 51.
  • 8% with o1-preview,while production Devin reached 74.

Quick Facts

Published
Updated
Source
Cognition 模型 / Devin 博客(网页)
Category
Tutorials & Tips
AI score
60
Read the original Read the full article at the original source
Why it matters

Cognition 作为 Devin 开发方给出 o1 系列的实测对比数据,并完整披露其内部基准 cognition-golden 的评测方法。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Cognition evaluates OpenAI o1 series on Devin coding agent and publishes evaluation method. September 12, 2024. https://new.nat6.net/en/news/swrpyrobyv7olq6awpfmlqkld/

View all →