Lennox Saint
Open menu

BuilderBenchby the LAB

30 September 2026 · v3 · pack 3.0.0
4-hour build window · Extra High (xhigh) · Standard

full result · owner-finalized partial personal assessment

GPT-6.1 Sol scored 41.75.

One owner-finalized partial review of one GPT-6.1 Sol run with Codex on the v3 pack. This is not a universal model ranking or a statistical claim.

words used on this page, in plain English
test (pack)
a fixed set of tasks. every AI in the same pack gets the same tasks, so scores only compare inside one pack.
score out of 100
70% how good the finished work was (quality), 20% how little help it needed (autonomy), 10% useful extras nobody asked for (proactivity).
harness
the app or tool that runs the AI, like Codex or Claude Code. the score belongs to the AI and its harness together.
cleared result
a result Lennox checked and approved for publishing.
owner review
Lennox reviewed and scored the work. some checks are automated, and on one result he asked Claude to rate some parts for him. each result page says which. each result is one review of one run per AI.
named or blind review
named: Lennox could see which AI made the work. blind: the names were hidden until the scores were saved.
partial review
some of the work could not be fully checked. the result page says which parts.
API estimate
what the run would have cost at the AI company's listed prices. it is an estimate, not what was paid.
reasoning (xhigh)
how hard the AI was set to think. xhigh means extra high, the highest setting used.

final scores out of 100

full result · BuilderBench test of 30 September 2026 · 1 AI on this page

Codex harnessfinal score

GPT-6.1 Sol

41.75/100

quality 70% of the score
41.07
autonomy 20%
30
proactivity 10%
70
US$14.71

API estimate in US dollars · see coverage below · 15 of 18 records priced
API equivalent · not a bill

GPT-6.1 Sol scored 41.75.

owner-finalized partial personal assessment. one run per setup. the limits are below.

how each score is built

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.

  • GPT-6.1 Sol: 28.75 + 6.00 + 7.00 = 41.75

dated references

every cleared score, by date. not a leaderboard.

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.

  1. GPT-6.1 Sol30 Sep 2026 · v3 · pack 3.0.0 · with Codex
    owner-finalized partial personal assessment · this result
    41.75
  2. Gemini 4 Neon19 Nov 2026 · v3 · pack 3.1.0 · with BuilderBench API harness
    owner-finalized partial personal review, with 3 of 28 ratings made by the bench's conductor (claude opus 5.5) and disclosed
    58.76
  3. Gemini 4 Hydrogen12 Nov 2026 · v3 · pack 3.1.0 · with BuilderBench API harness
    owner review, with 7 of 28 ratings made by claude and disclosed
    51.11
  4. Gemini 4 Carbon11 Nov 2026 · v3 · pack 3.1.0 · with BuilderBench API harness
    owner-finalized partial personal assessment
    49.04
  5. Opus 5.510 Nov 2026 · v3 · pack 3.1.0 · with Claude
    owner-finalized partial personal assessment
    74.25
  6. Fable 5.210 Nov 2026 · v3 · pack 3.1.0 · with Claude
    owner-finalized partial personal assessment
    69.43
  7. GPT-6.1 Terra27 Oct 2026 · v3 · pack 3.0.0 · with Codex
    owner-finalized partial personal review
    48.88
  8. Kimi K3.1 Pro27 Oct 2026 · v3 · pack 3.0.0 · with BuilderBench API harness (OpenRouter)
    owner-finalized partial personal review
    46.68
  9. Gemini 4 Argon14 Oct 2026 · v3 · pack 3.0.0 · with BuilderBench API harness
    owner-finalized partial personal review
    45.38
  10. Muse Wonder Full14 Oct 2026 · v3 · pack 3.0.0 · with Muse Code
    owner-finalized partial personal review
    39.91
  11. GPT-6 Luna8 Oct 2026 · v3 · pack 3.0.0 · with Codex
    owner-finalized partial personal assessment
    44.58
  12. Haiku 5.58 Oct 2026 · v3 · pack 3.0.0 · with Claude
    owner-finalized partial personal assessment
    39.18
  13. Sonnet 5.529 Sep 2026 · v3 · pack 3.0.0 · with Claude
    owner-finalized partial personal assessment
    48.98
  14. GPT-6 Astra26 Sep 2026 · v2 · pack 2.0.0 · with Codex
    personal assessment with accepted recording limitations
    53.75
  15. Opus 5.524 Sep 2026 · v1 · pack 1.0.0 · with Claude
    one owner-scored pilot
    68.26
  16. GPT-6 Sol24 Sep 2026 · v1 · pack 1.0.0 · with Codex
    one owner-scored pilot
    45.55

task breakdown

where it gained and lost ground

each task is scored out of 100. its weight is its share of the quality score.

swipe the table sideways to see every column.

Task scores out of 100 for each setup, with each task’s share of the quality score
taskGPT-6.1 Solscore /100
01 · Writing10% of quality26
02 · Landing page10% of quality30
03 · App lead magnet20% of quality30
04 · Video editing10% of quality16.67
05 · Motion5% of quality20
06 · Thumbnails10% of quality23
07 · Browser + computer10% of quality55
08 · Research10% of quality55
09 · Automation10% of quality100
10 · Founder conversations5% of quality70
see the API estimate for each task

swipe the table sideways to see every column.

API-equivalent estimate and usage coverage for each task and setup
taskGPT-6.1 SolAPI-equivalent estimate
WritingUS$0.50recorded usage
Landing pageUS$1.07partial usage
App lead magnetUS$4.13recorded usage
Video editingUS$5.32recorded usage
MotionUS$1.31partial usage
ThumbnailsUS$1.71recorded usage
Browser + computerunavailableusage unavailable
ResearchUS$0.22partial usage
AutomationUS$0.45recorded usage
Founder conversationsunavailableusage unavailable

estimates, not bills. “unavailable” means no usage was recorded for that task. it does not mean the task was free.

API pricing

rates, the run estimate and the bill are three different things.

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.

GPT-6.1 Sol

official API rates

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.

recorded estimate for this run
US$14.71API-equivalent estimate for recorded execution usage; 15 of 18 execution records priced.
actual bill
unknown. billing for this run: existing subscriptions. no receipted charge exists for it, and unknown is not zero.

API-equivalent estimates price recorded execution usage at published API rates. They are not bills. Missing native usage, setup, calibration, coordination, grading, presentation, subscription fees and unreceipted services are excluded. Actual incremental spend is unknown.

review conditions

how this run was reviewed

The owner rated the saved outputs of each of the ten v3 tasks, plus autonomy and proactivity, in a named single-model review. The saved scores were then finalized as a partial personal assessment and locked. Quality is the weighted task score. v1 to v3 use 70% quality, 20% autonomy and 10% proactivity.

who runs this: Lennox Saint. the v3 tasks come from real work for Threadify, the business he co-founded.

scores locked
yes
names revealed
yes, after lock

frozen setup

what was tested

pack version
3.0.0
build window
4 hours
reasoning
Extra High (xhigh)
speed
Standard
billing
Existing subscriptions
scored runs
1 per setup

exact model and harness version strings are not in this public export, so they stay unknown here.

limits

what this result does not prove

  • This is one owner-finalized partial personal assessment of one run, not a universal ranking.
  • Independent checks and native recordings did not finish. Saved outputs were assessed as delivered; the original execution and evidence remain incomplete.
  • The founder conversations ran in the owner's own Codex app with app memory on, not from the fixture-only source pack. The planning conversation ran in default mode, not plan mode, and its rating was saved before that conversation ended.
  • The score belongs to the full setup: model, harness, tools and settings.
  • Pack 3.0.0 scores compare only with other pack 3.0.0 results, not with v1 or v2 results.
  • The API-equivalent estimate covers 15 of 18 execution records. Tasks marked not recorded have no priced usage.
  • Actual incremental spend is unknown because the run used existing subscriptions.
  • The build window was four hours. Native live sessions were timed separately from the build window.
BuilderBench v3 result: GPT-6.1 Sol with Codex scored 41.75 out of 100 (quality 41.07, autonomy 30, proactivity 70) in an owner-finalized partial review. API-equivalent estimate US$14.71, partial usage.
the result graphic. owner-finalized partial personal assessment. costs are estimates, not bills. every number in it is also on this page as text.

p.s.

get the next BuilderBench result first.

  • the exact prompt i typed
  • what came back
  • where it fell over

free. unsubscribe any time, one click. privacy.

  • 34,473 on Threads
  • 3,612 readers
  • 1.91K on YouTube

live count, 22 nov 2026.