Deer-flow evaluation

[jxzhangjhu]

Hi Team,

Thanks for your efforts on this benchmark. Just curious if you would like to evaluate deer-flow deep research agents? https://github.com/bytedance/deer-flow

More than happy to learn how it works and compares with other API-based and open-sourced, e.g., open deep research by langchain.

thanks

[Ayanami0730]

Thanks for the excellent suggestion!

We agree, Deer-Flow is a very influential open-source project for deep research agents, and it would be a great addition to the benchmark.

We've added it to our evaluation queue. As soon as our team has the bandwidth, we will work on evaluating it and updating the leaderboard with the results.

We'll keep this issue open to track its progress. Thanks again for bringing it to our attention!