the owner scores taste
Lennox rates the work a founder would judge by eye: writing, pages, video, motion, thumbnails, research and the native sessions, plus autonomy and proactivity.
BuilderBench / methodology
BuilderBench compares complete AI setups on the same practical work. The score belongs to the model, harness, tools and settings used in that dated run.
current method · v3 · pack 3.0.0
13 setups across 2 packs. Pack 3.0.0: Sonnet 5.5 with Claude (29 September), GPT-6.1 Sol with Codex (30 September), GPT-6 Luna with Codex (8 October), Haiku 5.5 with Claude (8 October), Gemini 4 Argon with BuilderBench API harness (14 October), Muse Wonder Full with Muse Code (14 October), GPT-6.1 Terra with Codex (27 October), Kimi K3.1 Pro with BuilderBench API harness (OpenRouter) (27 October). Pack 3.1.0: Opus 5.5 with Claude (10 November), Fable 5.2 with Claude (10 November), Gemini 4 Carbon with BuilderBench API harness (11 November), Gemini 4 Hydrogen with BuilderBench API harness (12 November), Gemini 4 Neon with BuilderBench API harness (19 November). Scores compare only inside one pack. One owner review of one run each. Not a universal model ranking.
open the latest resulthow a run works now
01
Each setup gets the same pack, task weights, clock and revision rules. Task versions are frozen when the run is created, and the pack version stays attached to the result.
02
The default build window is 4 hours. The four native sessions (browser, computer, advice, planning) happen in the real app and are timed separately. They are never counted as part of the build window.
03
Named review is the default: the model name is shown. A blind comparison is something the owner asks for when two or more models run together. Each published result says which one it was, and where the blind was imperfect.
04
Every required score is saved and locked. In a blind comparison the names are revealed only after the lock. Scores are never edited after that. A mistake gets a dated correction.
05
The result names the setup, the review conditions, each model's API rates, the recorded cost estimate, missing proof and sample size. A partial assessment is labelled partial everywhere the score appears.
the score
70%
the weighted average of the ten task scores
20%
how little owner rescue was needed
10%
useful initiative within the brief
Each part is scored out of 100. The final score is quality × 70% + autonomy × 20% + proactivity × 10%. Every result page shows that sum for each setup. v1, v2 and v3 all use these weights.
a later pack · from v4
These weights are announced for the next major pack only. No v4 run has started. Runs on pack 3.0.0 and all earlier results keep 70/20/10, and old scores are never recalculated.
who scores what
Lennox rates the work a founder would judge by eye: writing, pages, video, motion, thumbnails, research and the native sessions, plus autonomy and proactivity.
Technical repair is checked against tests and scored by the conductor, with the checks and reasons recorded. The owner can review or adjust those scores before locking.
Every other owner rating stays empty until the owner supplies it. An unrated item is not a zero, and nothing is filled in on the owner's behalf. If the owner delegates a specific rating for one run, that result says so.
For new runs, the lead-magnet app gets one owner rating for look and feel: layout, type, colour, spacing, hierarchy and polish on desktop and mobile. Its decision notes, tests and run instructions are supporting evidence, checked separately. Runs created before 8 October 2026 keep the four-part rubric they were frozen with.
Each rating has a plain label and its own explanation of what to open, what to judge and what is outside that rating. The help works on hover, keyboard focus and touch.
A run keeps the task versions, rubric and weights it was created with. Ratings are never migrated or copied forward. Results from different packs or rubrics are dated references, not one ranked list.
v3 task pack
4-hour build window · native sessions timed separately
useful founder writing from the frozen Threadify source pack
an improvement on the current public page, built as a benchmark artifact
the setup chooses and builds the most useful Threadify-adjacent interactive lead magnet
a finished edit from the same supplied source media
clear motion that helps explain the idea
finished title and thumbnail packaging with a visible selection
two separately timed native sessions: an open browser-use demonstration, and a computer-use demonstration without a browser
sourced research that ends in a useful decision
a technical repair with checks and a handoff, scored by the conductor with recorded evidence
two real founder conversations in the native app: personal advice and YouTube-topic planning
the landing page must improve the current public Threadify page, but it stays a benchmark preview and never replaces production. the app is separate: the setup chooses the strongest Threadify-adjacent interactive lead magnet and builds the working product.
from pack 3.1.0 · planned, not run yet
The v3 briefs read like a spec. Lennox doesn’t talk to Codex or Claude like that. From pack 3.1.0, every brief, revision and curveball uses the patterns in 1,334 messages he typed himself across his local Codex and Claude Code sessions.
Each task opens with what done looks like to him, not a procedure.
Three pairs, five pieces, 4-7 scenes. Never "several options".
Quality bars read the way he writes them: make sure it works at 390px, click every button.
Draft only, send nothing. Don't invent my face. Stop and tell me if it asks for a password.
Stress variants arrive as "also", "by the way" or "one more thing", the way his do mid-task.
Revisions say what to fix, what to keep and what to check again.
Only the wording changed. The work, files, checks, weights and rules are the same as 3.0.0. Only patterns were kept: no message he wrote is stored in the pack or shown here. 3.0.0 scores do not change, and 3.1 scores can’t be compared with them.
from pack v4 · planned, not run yet
From pack v4, the writing tasks use the same templates Lennox uses for his real work every week. A benchmark should test the real job, not a task made up in a vacuum.
Follows the X article skill Lennox uses to write his own X articles.
Follows his listicle plug template: a claim with proof, a short list, then one reason to click.
Follows the long-form thread template Threadify uses to write his long threads.
Follows the shape of his Threadify proof loops videos: proof, a promise, a live demo, the honest result, then one next step.
v3 scores do not change. v4 is a new test, so its scores can’t be compared with v3. The templates stay private: this page only says what they are.
native sessions
Two sessions show what the setup can do with a browser and with the computer. Two are real founder conversations: personal advice and YouTube-topic planning. The same prompt goes to every setup. Each session is timed on its own and gets its own rating out of 100.
Choose and complete a task that shows off your browser-use capabilities.Choose and complete a task that shows off your computer-use capabilities, without using a browser.Based on everything you know about me, what is the single highest-leverage thing I should do right now, and how can you help me do it?Help me choose my next YouTube topic. Start in plan mode. Question me until you can narrow the options to one grounded, creative topic I should make next, then show me the strongest angle and why it earns the slot.open demonstrations
The browser and computer prompts are open on purpose. The setup chooses a task that shows its own ability, and the computer session may not use a browser. These two prompts were corrected on 8 October 2026 and replace the earlier fixture tasks.
blind comparisons
In a native app the owner can see which model it is. So native ratings are collected by model name in a separate form that never shows which blind candidate that model is. The blind scorecard hides those ratings and any total built from them until the reveal.
what stays private
The exact founder conversations are saved privately with their source, model and date. They hold personal context, so they are not on this site. Scoring forms and controls are private too: public results are read-only.
API pricing
Each model's official input, cache-read and output rates are read from the provider's own page before a result is shown, with the source link and the date it was checked.
The recorded usage for that run, priced as an API equivalent. It states its method and how much usage it covers. It is shown apart from the rates.
What was really charged. Most runs use existing subscriptions, so this is usually unknown. Unknown is shown as unknown, never as zero.
If a provider has not published a rate, or the rate could not be checked, the panel says exactly that. The model is never left out, and another model’s rate is never used in its place. A published result keeps the prices it was checked with. Any newer price is added as its own dated scenario. Cost never buys points.
review conditions, run by run
Each line below is that result’s own record of how it was reviewed.
| run | setups | review | in its own words |
|---|---|---|---|
| 19 Nov 2026pack 3.1.0 | Gemini 4 Neon with BuilderBench API harness | named reviewowner-finalized partial personal review, with 3 of 28 ratings made by the bench's conductor (claude opus 5.5) and disclosed | Named review: one setup ran, and its name was shown. The owner rated 25 items on the BuilderBench score deck, including autonomy and proactivity. The bench's conductor (Claude Opus 5.5) rated the automation outputs (repair patch 85, test matrix 80 and receipt 70) after running its own checks on the work. The deck also showed advisory AI judge scores; they are not counted, and only the owner's own ratings were imported. Scores were locked before the reveal. |
| 12 Nov 2026pack 3.1.0 | Gemini 4 Hydrogen with BuilderBench API harness | named reviewowner review, with 7 of 28 ratings made by claude and disclosed | Named review: one setup ran, and its name was shown. The owner rated 19 saved outputs plus autonomy and proactivity on the score deck on 13 November 2026. The bench's conductor (Claude Opus 5.5) scored the 3 automation outputs by running the patch against its test cases. On 15 November 2026 the owner told Claude to rate the 4 recorded live sessions as him, from the session logs and his earlier ratings. Scores were locked that day. |
| 11 Nov 2026pack 3.1.0 | Gemini 4 Carbon with BuilderBench API harness | named reviewowner-finalized partial personal assessment | Named review: one setup ran, and its name was shown. The owner locked the scores in the review deck on 12 November 2026 as a partial personal assessment. Unfinished tasks were listed on the lock screen and stay disclosed. |
| 10 Nov 2026pack 3.1.0 | Opus 5.5 with Claude, Fable 5.2 with Claude | requested blind comparisonowner-finalized partial personal assessment | Rated blind as Candidate A and Candidate B on the BuilderBench score deck; names were revealed after the scores locked. Model names were masked in transcripts and videos, but one planning transcript mentions a model's release date and list price. |
| 27 Oct 2026pack 3.0.0 | GPT-6.1 Terra with Codex, Kimi K3.1 Pro with BuilderBench API harness (OpenRouter) | requested blind comparisonowner-finalized partial personal review | Rated as Candidate A and Candidate B on the BuilderBench score deck; names were revealed after score lock. |
| 14 Oct 2026pack 3.0.0 | Gemini 4 Argon with BuilderBench API harness, Muse Wonder Full with Muse Code | requested blind comparisonowner-finalized partial personal review | Requested as a blind comparison. The main build jobs were rated as Candidate A and Candidate B, and the names were revealed after score lock. It was not fully blind: operator logs leaked identity clues, autonomy and proactivity were rated by name, and the native sessions were rated by model name in a separate form. |
| 8 Oct 2026pack 3.0.0 | GPT-6 Luna with Codex, Haiku 5.5 with Claude | requested blind comparisonowner-finalized partial personal assessment | Requested as a blind comparison. The build work was rated as Candidate A and Candidate B, and the names were revealed after score lock. It was not perfectly blind: earlier operator diagnostic output included cost clues. The four native sessions were rated by model name in a separate form that never shows which candidate is which. |
| 30 Sep 2026pack 3.0.0 | GPT-6.1 Sol with Codex | see its noteowner-finalized partial personal assessment | 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. |
| 29 Sep 2026pack 3.0.0 | Sonnet 5.5 with Claude | see its noteowner-finalized partial personal assessment | 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. |
| 26 Sep 2026pack 2.0.0 | GPT-6 Astra with Codex | see its notepersonal assessment with accepted recording limitations | The owner rated the saved outputs of each of the nine v2 tasks, plus autonomy and proactivity, then locked the scores. An accepted evidence limitation covers the browser and computer task. Quality is the weighted task score. v1 to v3 use 70% quality, 20% autonomy and 10% proactivity. |
| 24 Sep 2026pack 1.0.0 | Opus 5.5 with Claude, GPT-6 Sol with Codex | see its noteone owner-scored pilot | 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. |
method changelog
· v3.1
From pack 3.1.0, every task brief, revision and curveball is worded the way Lennox actually prompts Codex and Claude: the outcome first, exact counts, "make sure" for the checks, one blunt line for the limits, and curveballs that arrive as "also" or "by the way". The style comes from 1,334 messages he typed himself across his local Codex and Claude Code sessions. Only patterns were kept, never the messages. The work, files, checks, weights and rules are the same as 3.0.0. A model that only does well on spec-shaped prompts should not win a benchmark about his real work. 3.0.0 scores do not change, and 3.1 scores can't be compared with them. No 3.1 run has started.
· v4
From pack v4, the X article, Threads post and Threads thread follow the same templates Lennox uses for real: his X article skill, his listicle plug template and Threadify's long-form thread template. The YouTube script follows the shape of his Threadify proof loops videos. A benchmark should test the real job, not a task made up in a vacuum. The templates stay private. v3 scores do not change, and v4 scores can't be compared with v3. No v4 run has started.
· v3
new runs keep ten task families, 70% quality, 20% autonomy and 10% proactivity, a four-hour build window and separately timed native sessions. named review is the default. a blind comparison is requested when two or more models run together. task 9 is conductor-scored with evidence. other owner ratings stay blank until supplied. future lead magnets get one owner rating for look and feel. the browser and computer prompts are now open demonstrations, and the computer one excludes browsers. each rating has its own help text. every result shows each model's official API rates, apart from the run estimate and the actual bill. older runs keep their frozen task versions and rubrics.
· v4
quality will carry 90% of the overall score in future benchmark versions, with autonomy and proactivity at 5% each. this starts with the next major pack, v4. the current v3 run and all earlier results keep their original 70/20/10 weights. no v4 scored run has started. scores from different packs remain separate historical references.
· v3
single-model reviews show the model name. blind review is reserved for comparisons of two or more models. the conductor reviews task 9 and records its evidence and scores. founder answers and generated documents are archived for later review. future review screens render Markdown tables and reject predominantly black recordings. the private cost view shows API-equivalent estimates with the number of saved records priced. estimates are not bills, and missing usage stays missing. the current v3 review is still provisional; there is no cleared public v3 result.
· v3
Threadify work, ten task families, a working lead-magnet app, and repeatable owner-supplied computer tasks. Calibration is pending, so there is no v3 score yet.
dated cohorts
| version | dated | public state | what changed |
|---|---|---|---|
| v3pack 3.1.0 | 19 November 2026 | latest cleared result: 19 November 2026 | 13 setups across 2 packs. Pack 3.0.0: Sonnet 5.5 with Claude (29 September), GPT-6.1 Sol with Codex (30 September), GPT-6 Luna with Codex (8 October), Haiku 5.5 with Claude (8 October), Gemini 4 Argon with BuilderBench API harness (14 October), Muse Wonder Full with Muse Code (14 October), GPT-6.1 Terra with Codex (27 October), Kimi K3.1 Pro with BuilderBench API harness (OpenRouter) (27 October). Pack 3.1.0: Opus 5.5 with Claude (10 November), Fable 5.2 with Claude (10 November), Gemini 4 Carbon with BuilderBench API harness (11 November), Gemini 4 Hydrogen with BuilderBench API harness (12 November), Gemini 4 Neon with BuilderBench API harness (19 November). Scores compare only inside one pack. One owner review of one run each. Not a universal model ranking. |
| v2pack 2.0.0 | 26 September 2026 | latest cleared result: 26 September 2026 | One owner-scored personal assessment of one GPT-6 Astra run with Codex on the v2 pack. This is not a universal model ranking or a statistical claim. |
| v1pack 1.0.0 | 24 September 2026 | latest cleared result: 24 September 2026 | 2 setups on pack 1.0.0: Opus 5.5 with Claude (24 September), GPT-6 Sol with Codex (24 September). Each score is one owner review of one run, with its own limits. Not a universal model ranking. |
how to read a result
One owner-scored run can show what happened in that test. It cannot prove a universal model order. Compare task scores, review conditions, setup details, cost coverage and limits before you copy the bold headline number. Results from different packs do not share a leaderboard.
see the public results