/Auto-GPT-Benchmarks

A repo built for the purpose of benchmarking the performance of agents, regardless of how they are set up and how they work.

Primary LanguageJupyter NotebookMIT LicenseMIT

This repo is currently deprecated. For the updated benchmark view the main repo at https://github.com/Significant-Gravitas/AutoGPT in the benchmark folder.

Auto-GPT Benchmarks

Built for the purpose of benchmarking the performance of agents regardless of how they work.

Objectively know how well your agent is performing in categories like code, retrieval, memory, and safety.

Save time and money while doing it through smart dependencies. The best part? It's all automated.

Scores:

Screenshot 2023-07-25 at 10 35 01 AM

Ranking overall:

Detailed results:

Screenshot 2023-07-25 at 10 42 15 AM

Click here to see the results and the raw data!!

More agents coming soon !