wangjunxiao/ponytail
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: benchmark chart — ponytail vs caveman vs control

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
dgebert
2026-06-12 12:18:18 +02:00
co-authored by Claude Fable 5
parent 983255e2a1
commit b609e019a0
2 changed files with 78 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+9 -1
View File
@@ -73,7 +73,15 @@ You know exactly why.
## Numbers
5 coding tasks, same agent with and without ponytail: **−16% tokens, ~4× faster, 293 → 47 lines.** The 246 lines nobody wrote have never caused an incident. Data: [benchmarks/](benchmarks/).
5 coding tasks, same agent with and without ponytail: **−16% tokens, ~4× faster, 293 → 47 lines.** The 246 lines nobody wrote have never caused an incident.
Then six harder tasks — streaming parsers, atomic file sync, auth, a concurrent money ledger — against a no-skill control and the [caveman](https://github.com/JuliusBrussee/caveman) skill, with adversarial security and concurrency probes:
<p align="center">
<img src="assets/benchmark-loc.svg" width="860" alt="Lines of code per task: ponytail 490 total vs caveman 1,440 vs control 2,943 — all passing the same adversarial probes">
</p>
Everyone passes every probe. Ponytail does it with a third of caveman's code, a sixth of control's, and was ~5× cheaper when the surprise feature request landed (96 lines changed vs 487 for control). Every shortcut is marked in-code with its upgrade path. Data: [benchmarks/](benchmarks/).
## License