Can you open-source the evaluation results of GPT4?

OSU-NLP-Group / TravelPlanner

[ICML'24 Spotlight] "TravelPlanner: A Benchmark for Real-World Planning with Language Agents"

https://osu-nlp-group.github.io/TravelPlanner/

MIT License

215 stars 27 forks source link

Closed kleinzcy closed 3 weeks ago

kleinzcy commented 1 month ago

Hi, it is a great work to evaluate the LLM's ability in complex reasoning. can you opensource an log for GPT4 which sucessfully make a plan?

hsaest commented 3 weeks ago

Hi,

Thank you for your interest in our work and sorry for the delayed reply.

Please refer to this for GPT-4-Turbo generated plans on val set.

Feel free to contact us if you have further questions.

Best, Jian