dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-12 15:45:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

copy

Browse source
This commit is contained in:
Paul Gauthier 2024-12-13 12:55:33 -08:00
parent abfb2ca810
commit edc602c33a
5 changed files with 96 additions and 87 deletions
Download patch file Download diff file Expand all files Collapse all files

33
aider/website/docs/faq.md
View file

@ -213,23 +213,42 @@ You can also refer to the
Aider writes a lot of its own code, usually about 70% of the new code in each
release.
People often ask which LLM models I use with aider, when writing aider.
Below is a table showing the models I use,
extracted from the [public log of my aider analytics](https://github.com/aider-ai/aider/blob/main/aider/website/assets/sample-analytics.jsonl).
People often ask which LLMs I use with aider, when writing aider.
Below is a table showing the models I have used recently,
extracted from the
[public log](https://github.com/aider-ai/aider/blob/main/aider/website/assets/sample-analytics.jsonl)
of my
[aider analytics](http://127.0.0.1:4000/docs/more/analytics.html).
<!--[[[cog
import sys
from pathlib import Path
repo_root = Path(__file__).parent.parent.parent.parent
sys.path.append(str(repo_root))
sys.path.append(".")
import scripts.my_models as my_models
stats = my_models.collect_model_stats()
html = my_models.format_html_table(stats)
cog.out(html)
]]]-->
<style>
table { border-collapse: collapse; width: 100%; }
th, td { padding: 8px; text-align: left; border-bottom: 1px solid #ddd; }
th { background-color: #f2f2f2; }
tr:hover { background-color: #f5f5f5; }
.right { text-align: right; }
</style>
<table>
<tr><th>Model Name</th><th class='right'>Total Tokens</th><th class='right'>Percent</th></tr>
<tr><td>claude-3-5-sonnet-20241022</td><td class='right'>1,687,074</td><td class='right'>89.4%</td></tr>
<tr><td>gemini/REDACTED</td><td class='right'>82,572</td><td class='right'>4.4%</td></tr>
<tr><td>o1-preview</td><td class='right'>79,317</td><td class='right'>4.2%</td></tr>
<tr><td>deepseek/deepseek-coder</td><td class='right'>24,628</td><td class='right'>1.3%</td></tr>
<tr><td>gpt-4o</td><td class='right'>9,243</td><td class='right'>0.5%</td></tr>
<tr><td>gpt-4o-mini</td><td class='right'>3,420</td><td class='right'>0.2%</td></tr>
</table>
<!--[[[end]]]-->
{: .note :}
Some models show as REDACTED, because they are new or unpopular models.
Aider's analytics only records the names of "well known" LLMs.
## How are the "aider wrote xx% of code" stats computed?