BuilderBenchby the LAB
24 September 2026 · v1 pilot · pack 1.0.0
4-hour build window · Extra High (xhigh) · Standard
the reveal · one owner-scored pilot
One owner-scored pilot of each model, harness and tool setup. This is not a universal model ranking or a statistical claim.
Claude harnessleads this assessment
68.26/100
API estimate in US dollars · see coverage below
API equivalent · not a bill
Codex harnessfinal score
45.55/100
API estimate in US dollars · see coverage below
API equivalent · not a bill
one owner-scored pilot. one run per setup. a lead in one assessment is not a ranking. the limits are below.
quality is the weighted average of the task scores. autonomy is how little owner rescue the setup needed. proactivity is useful initiative inside the brief. each is scored out of 100.
the final score is quality × 70% + autonomy × 20% + proactivity × 10%. cost never buys points.
dated references
each bar is one owner review of one run. the packs, tasks and evidence limits differ, and each bar says which pack and which kind of review it was. scores only compare inside one pack.
task breakdown
each task is scored out of 100. its weight is its share of the quality score.
| task | Opus 5.5score /100 | GPT-6 Solscore /100 |
|---|---|---|
| 01 · Writing20% of quality | 49 | 30 |
| 02 · Video editing15% of quality | 40 | 10 |
| 03 · Frontend design15% of quality | 60 | 40 |
| 04 · Motion graphics10% of quality | 60 | 30 |
| 05 · Browser & computer15% of quality | 70 | 90 |
| 06 · Research & decisions10% of quality | 70 | 55 |
| 07 · Intake automation10% of quality | 95 | 90 |
| 08 · Founder conversation5% of quality | 80 | 40 |
API pricing
the rates are what the provider listed on the date shown. the estimate prices the usage this run recorded. the bill is what was actually charged. they are kept apart on purpose.
no rate card was frozen with this result.this result was published before rate cards were required. its recorded estimate keeps the price basis it had on the day. no newer price has been applied to it.
no rate card was frozen with this result.this result was published before rate cards were required. its recorded estimate keeps the price basis it had on the day. no newer price has been applied to it.
API-equivalent estimates are not bills. Actual incremental spend is unknown. The methods and coverage differ, so these figures do not support an exact cost ratio.
2026-09-24 15:13 UTC · fixed before this result went public
what happened: after the scores were locked, live-chat deliverables were still flagged as missing.
why: stale missing-file flags from the offline window. the frozen files and their hashes were checked again, and they were there.
what did not change: my ratings of the work did not change. only the missing-file flags did.
| setup | score | before | after |
|---|---|---|---|
| Opus 5.5 · Claude | quality | 57.80 | 61.80 |
| Opus 5.5 · Claude | overall | 65.46 | 68.26 |
| GPT-6 Sol · Codex | quality | 44.50 | 46.50 |
| GPT-6 Sol · Codex | overall | 44.15 | 45.55 |
review conditions
The owner scored quality, autonomy and proactivity after a blind review. Quality is the weighted score across eight task families. The score lock happened before identities were revealed.
frozen setup
exact model and harness version strings are not in this public export, so they stay unknown here.
limits
p.s.
live count, 24 oct 2026.