recipe-maintainers/agent-orchestrator-benchmark
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: finalize deferred at N=5 (median 12.89M, ~tied with orig)

Browse Source
This commit is contained in:
mfowler
2026-06-16 02:12:12 +00:00
parent 3bf3316572
commit 8e6290e7e0
3 changed files with 18 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
RESULTS-campaign.md
View File

@ -1,6 +1,6 @@
# Full-harness benchmark — campaign analysis
Real `agents.py up` Builder/Adversary loop pair + watchdog through the 3-phase calculator to SEQUENCE-COMPLETE. Both loops on Sonnet. Tokens summed from each loop's session transcript; commits = work-repo commit count; LOC = non-blank `calc/*.py` lines (code + tests). 28 successful runs of 30 total.
Real `agents.py up` Builder/Adversary loop pair + watchdog through the 3-phase calculator to SEQUENCE-COMPLETE. Both loops on Sonnet. Tokens summed from each loop's session transcript; commits = work-repo commit count; LOC = non-blank `calc/*.py` lines (code + tests). 30 successful runs of 33 total.
## Per-variant total tokens (successful runs)
@ -11,7 +11,7 @@ Real `agents.py up` Builder/Adversary loop pair + watchdog through the 3-phase c
| builder-adversary-stateless | 5/5 | 10,122,375 | 10,735,401 | 9,992,834 | 13,009,792 | 1.30x |
| builder-adversary-lean | 5/6 | 13,409,349 | 13,216,582 | 12,101,355 | 13,815,595 | 1.14x |
| builder-solo | 5/5 | 2,773,634 | 2,744,840 | 2,417,528 | 2,948,467 | 1.22x |
| builder-adversary-deferred | 3/3 | 13,366,800 | 13,863,041 | 12,888,082 | 15,334,242 | 1.19x |
| builder-adversary-deferred | 5/6 | 12,888,082 | 12,410,637 | 9,610,923 | 15,334,242 | 1.60x |
## Efficiency ratios — min / median / max (successful runs)
@ -24,8 +24,8 @@ tokens/sec excludes runs flagged `LIMIT` (a usage-limit pause inflates duration
| builder-adversary-stateless | 21,802 / 27,799 / 30,861 | 10,544 / 11,620 / 12,755 | 697,172 / 765,282 / 778,644 |
| builder-adversary-lean | 28,077 / 33,238 / 38,966 | 12,416 / 13,523 / 14,403 | 432,191 / 478,905 / 575,650 |
| builder-solo | 6,029 / 6,611 / 6,969 | 6,542 / 6,715 / 7,020 | 392,494 / 483,506 / 737,117 |
| builder-adversary-deferred | 31,451 / 33,827 / 34,537 | 12,170 / 13,105 / 15,343 | 1,277,854 / 1,336,680 / 1,841,155 |
| **all** | 6,029 / 29,024 / 38,966 | 6,542 / 12,170 / 15,814 | 392,494 / 705,228 / 1,841,155 |
| builder-adversary-deferred | 20,107 / 31,451 / 34,537 | 12,170 / 13,349 / 15,343 | 739,302 / 1,277,854 / 1,841,155 |
| **all** | 6,029 / 28,410 / 38,966 | 6,542 / 12,416 / 15,814 | 392,494 / 716,723 / 1,841,155 |
## Per-variant medians (commits / LOC / duration)
@ -36,15 +36,15 @@ tokens/sec excludes runs flagged `LIMIT` (a usage-limit pause inflates duration
| builder-adversary-stateless | 14 | 400 | 900 |
| builder-adversary-lean | 28 | 390 | 960 |
| builder-solo | 5 | 426 | 420 |
| builder-adversary-deferred | 10 | 425 | 1020 |
| builder-adversary-deferred | 12 | 425 | 840 |
## Correlations with total tokens (pooled, n=28)
## Correlations with total tokens (pooled, n=30)
| tokens vs | Pearson r |
|---|--:|
| duration | +0.83 |
| commits | +0.65 |
| LOC | +0.01 |
| commits | +0.64 |
| LOC | -0.00 |
## All runs (raw)
@ -80,5 +80,8 @@ tokens/sec excludes runs flagged `LIMIT` (a usage-limit pause inflates duration
| builder-adversary-deferred | 1 | YES | | 13,366,800 | 1020 | 10 | 425 | 31,451 | 13,105 | 1,336,680 |
| builder-adversary-deferred | 2 | YES | | 12,888,082 | 840 | 7 | 381 | 33,827 | 15,343 | 1,841,155 |
| builder-adversary-deferred | 3 | YES | | 15,334,242 | 1260 | 12 | 444 | 34,537 | 12,170 | 1,277,854 |
| builder-adversary-deferred | 4 | NO | | 8,536,729 | 2700 | 6 | 146 | 58,471 | 3,162 | 1,422,788 |
| builder-adversary-deferred | 5 | YES | | 9,610,923 | 720 | 13 | 478 | 20,107 | 13,349 | 739,302 |
| builder-adversary-deferred | 1 | YES | | 10,853,138 | 780 | 12 | 421 | 25,779 | 13,914 | 904,428 |
_Stats over successful runs. `LIMIT` = the run hit a usage-limit pause (duration/tok-sec distorted, token total fine). Repos kept under the run root for analysis._