Start showing benchmark results (#100)

This commit is contained in:
merwanehamadi
2023-07-14 14:56:56 -07:00
committed by GitHub
parent 7bc7d9213d
commit 281cb0ef37

View File

@@ -2,13 +2,26 @@
A repo built for the purpose of benchmarking the performance of agents far and wide, regardless of how they are set up and how they work
### Scores:
## Scores:
Spider chart for each agent coming soon !
Scoring of agents will go here. Both overall and by category.
## Detailed results
:warning: These results are constantly evolving at the moment. We will publish an official benchmark result very soon.
### Integrated Agents
### Auto-GPT
Coming Soon!
- Auto-GPT
- gpt-engineer
- mini-agi
- smol-developer
### gpt-engineer
| Task | Results |
|-----------------------------------|----------------------|
| Debug Simple Typo With Guidance | :x: |
| Debug Simple Typo Without Guidance| :x: |
| Basic Code Generation | :white_check_mark: |
| Create Simple Web Server | :x: |
### mini-agi
Coming Soon!
### smol-developer
Coming Soon!