Significant-Gravitas
/
AutoGPT
mirror of https://github.com/Significant-Gravitas/AutoGPT.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
AutoGPT/benchmark
History
Reinier van der Leer db0e726954 fix(agent, benchmark): Specify `path_type=Path` for CLI path options/arguments 
Without `path_type=Path`, an option/argument with `type=click.Path()` will return a `str`.
 		2024-07-03 15:21:04 -06:00
..
.vscode Auto-GPT-20230905085638 2023-09-05 10:10:03 -07:00
agbenchmark fix(agent, benchmark): Specify `path_type=Path` for CLI path options/arguments 2024-07-03 15:21:04 -06:00
agbenchmark_config Add more challenges + cleanup (#5368) 2023-09-27 17:58:58 -07:00
backend Refactor benchmark (#5247) 2023-09-17 06:55:20 -07:00
frontend Fix challenges (#5561) 2023-10-05 10:59:50 -07:00
reports fix(agent, benchmark): Specify `path_type=Path` for CLI path options/arguments 2024-07-03 15:21:04 -06:00
tests Set up unified pre-commit + CI w/ linting + type checking & FIX EVERYTHING (#7171) 2024-05-28 05:04:21 +02:00
.env.example feat(benchmark): Make report output folder configurable 2024-02-15 18:07:45 +01:00
.flake8 Set up unified pre-commit + CI w/ linting + type checking & FIX EVERYTHING (#7171) 2024-05-28 05:04:21 +02:00
.gitignore Add eval_id and sync Skill Tree with Frontend(#5287) 2023-09-21 13:36:17 -07:00
.python-version Auto-GPT-20230905085638 2023-09-05 10:10:03 -07:00
LICENSE clean(benchmark): Remove Depreciated Challenges (#7144) 2024-05-20 15:01:36 +02:00
README.md Rename Auto-GPT to AutoGPT (#5301) 2023-09-22 15:49:29 -07:00
agents_to_benchmark.json Rename Auto-GPT to AutoGPT (#5301) 2023-09-22 15:49:29 -07:00
poetry.lock feat(forge, agent, benchmark): Upgrade to Pydantic v2 (#7280) 2024-07-02 20:45:32 +02:00
pyproject.toml feat(forge, agent, benchmark): Upgrade to Pydantic v2 (#7280) 2024-07-02 20:45:32 +02:00
run.sh Fixing benchmarks 2023-09-11 17:41:27 -07:00

README.md

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 !