aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2026-01-31 11:54:30 +01:00
Code Issues Packages Projects Releases Wiki Activity
Files
7fda0c78848dcc2e74507ee4d3d599f181286e1e
Auto-GPT/benchmark
History
merwanehamadi 295702867a Ability to run by categories (#5229) 
* Ability to run by categories

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

* always use Path.cwd()

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

---------

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-15 20:04:12 -07:00
..
.vscode
Auto-GPT-20230905085638
2023-09-05 10:10:03 -07:00
agbenchmark
Ability to run by categories (#5229)
2023-09-15 20:04:12 -07:00
agbenchmark_config
Support agent protocol in benchmark (#5213)
2023-09-13 18:50:39 -07:00
agent_protocol_client
Ability to run by categories (#5229)
2023-09-15 20:04:12 -07:00
backend
benchmark-fix
2023-09-11 21:37:23 -07:00
frontend
small data changes
2023-09-11 18:20:03 -07:00
notebooks
Auto-GPT-20230905085638
2023-09-05 10:10:03 -07:00
reports
Merge branch 'master' into feat/monitor
2023-09-11 18:21:52 -07:00
.env.example
Auto-GPT-20230905085638
2023-09-05 10:10:03 -07:00
.flake8
Auto-GPT-20230905085638
2023-09-05 10:10:03 -07:00
.gitignore
Ability to run by categories (#5229)
2023-09-15 20:04:12 -07:00
.pre-commit-config.yaml
Auto-GPT-20230905085638
2023-09-05 10:10:03 -07:00
.python-version
Auto-GPT-20230905085638
2023-09-05 10:10:03 -07:00
agents_to_benchmark.json
Name agents like their github repos
2023-09-07 17:25:50 -07:00
LICENSE
Auto-GPT-20230905085638
2023-09-05 10:10:03 -07:00
mypy.ini
Auto-GPT-20230905085638
2023-09-05 10:10:03 -07:00
poetry.lock
add benchmark endpoints mock (#5221)
2023-09-15 08:48:12 -07:00
pyproject.toml
add benchmark endpoints mock (#5221)
2023-09-15 08:48:12 -07:00
README.md
Auto-GPT-20230905085638
2023-09-05 10:10:03 -07:00
run.sh
Fixing benchmarks
2023-09-11 17:41:27 -07:00
server.py
Add back api mode
2023-09-06 22:51:45 -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 !