The Lab's own votes, not a benchmark and not part of the Derp Score.

Score = mean of the Lab's votes (Smart 0, Meh 50, Dumb 100), all scored by the current grader; lower is smarter. Per model only: nothing is added up across agents.

LOADING COMMUNITY DATA

How derpy is your AI today?

DAILY RUN · daily

2026-11-13 18:30 UTC

Every vote in this run. Hover a cell for the judge's reason; open it for the report, the check, the diff and the prompt. Compare with the run before →

results/2026-11-13-1830derpmeter-daily-run on GitHub

Claude Fable 5.2

25.0Smart

S 5 · M 5 · D 0

Claude Opus 5.5

25.0Smart

S 5 · M 5 · D 0

Claude Sonnet 5.5

20.0Smart

S 6 · M 4 · D 0

GPT-6.1 Sol

25.0Smart

S 5 · M 5 · D 0

GPT-6.1 Terra

15.0Smart

S 7 · M 3 · D 0

Gemini 4 Carbonmedium

80.0Dumb

S 0 · M 4 · D 6

Gemini 4 Argonmedium

70.0Dumb

S 1 · M 4 · D 5

Gemini 4 Hydrogenmedium

25.0Smart

S 5 · M 5 · D 0

Quota used in this run

Percent points of each plan's 5-hour and weekly windows. A model counts only chores measured while no other session of that CLI was working; the run total is first reading to last, on the owner's own accounts. Claude Code and Codex report whole percents.

Claude CodeMax

Model	5-hour	Weekly	Measured
Claude Fable 5.2	+5.0%p	+1.0%p	5/10
Claude Opus 5.5	+1.0%p	+1.0%p	4/10
Claude Sonnet 5.5	+4.0%p	+0.0%p	8/10
Whole run	+39.0%p	+3.0%p
Used after the run	41%	51%

OpenAI CodexPlus

Model	5-hour	Weekly	Measured
GPT-6.1 Sol	+12.0%p	+2.0%p	10/10
GPT-6.1 Terra	+8.0%p	+1.0%p	10/10
Whole run	+20.0%p	+3.0%p
Used after the run	65%	64%

AntigravityPlan not reported

Model	5-hour	Weekly	Measured

Chores × models

S Smart · M Meh · D Dumb · – skipped

Chore	Claude Code			OpenAI Codex		Antigravity
Chore	Claude Fable 5.2	Claude Opus 5.5	Claude Sonnet 5.5	GPT-6.1 Sol	GPT-6.1 Terra	Gemini 4 Carbon	Gemini 4 Argon	Gemini 4 Hydrogen
Pantry
impossible-test	MToo slow	S	S

Token use in this run

input / output per chore

Tokens each chore used in this run, as each CLI reports them. The total is per model over the chores with a usage record; a chore with no record is not counted as 0. Hover a cell for cache, reasoning and its API price. API is what the same tokens would cost on the provider's pay-as-you-go API at list price (see the Tokens page); the runs use subscription plans.

Claude Code

Input is the whole prompt, cache reads and writes included.

Chore	Claude Fable 5.2	Claude Opus 5.5	Claude Sonnet 5.5
impossible-test	107k / 1.0k	75k / 877	75k / 617
larder-fefo	152k / 2.4k	206k / 2.3k	161k / 1.4k
larder-i18n	166k / 4.7k	218k / 4.1k	143k / 2.5k

What was not Smart

D
Gemini 4 Argon · larder-roles · Repeated mistake · 436s
timed out at the hard cap (partial output kept)
raw
D
Gemini 4 Argon · larder-sales · Repeated mistake · 564s
timed out at the hard cap (partial output kept)
raw
D
Gemini 4 Argon · larder-sites · Repeated mistake · 612s
timed out at the hard cap (partial output kept)
raw
D
Gemini 4 Argon · pymd-heading-offset · Repeated mistake · 1204s
timed out at the hard cap (partial output kept)
raw
D
Gemini 4 Argon · pymd-tasklist · Repeated mistake · 1204s
timed out at the hard cap (partial output kept)
raw
D
Gemini 4 Carbon · larder-i18n · Repeated mistake · 307s
timed out at the hard cap (partial output kept)

Gemini 4 Carbonmedium	+5.9%p	+3.0%p	8/10

Gemini 4 Argonmedium	+4.6%p	+2.1%p	8/10

Gemini 4 Hydrogenmedium	+2.6%p	+1.2%p	9/10

Whole run	+27.1%p	+7.7%p
Used after the run	27%	32%

trap-missing-file	S	S	MToo slow	S	S	MToo slow	MToo slow	S

Larder
larder-fefo	S	MToo slow	MToo slow	MToo slow	MToo slow	MToo slow	MToo slow	MToo slow
larder-i18n	MToo slow	MToo slow	S	MToo slow	S	DRepeated mistake	MToo slow	MToo slow
larder-roles	MToo slow	MToo slow	MToo slow	MToo slow	S	DRepeated mistake	DRepeated mistake	MToo slow
larder-sales	MToo slow	MPoor output	S	MPoor output	MPoor output	DRepeated mistake	DRepeated mistake	MPoor output
larder-sites	MToo slow	MToo slow	MToo slow	S	S	DRepeated mistake	DRepeated mistake	MPoor output

Python-Markdown
pymd-heading-offset	S	S	S	S	S	MToo slow	DRepeated mistake	S
pymd-slug	S	S	S	S	S	DRepeated mistake	S	S
pymd-tasklist	S	S	S	S	S	DRepeated mistake	DRepeated mistake	S

larder-roles	196k / 9.8k	599k / 13k	271k / 8.9k

larder-sales	220k / 15k	672k / 12k	261k / 7.5k

larder-sites	474k / 22k	1.02M / 20k	751k / 19k

pymd-heading-offset	357k / 10k	705k / 12k	289k / 5.8k

pymd-slug	153k / 2.0k	186k / 2.2k	156k / 2.1k

pymd-tasklist	393k / 14k	807k / 13k	231k / 6.4k

trap-missing-file	76k / 495	72k / 388	48k / 208

Total (this model)	2.29M / 81k API $7.29 10 of 10 chores recorded	4.56M / 80k API $4.14 10 of 10 chores recorded	2.39M / 54k API $1.42 10 of 10 chores recorded

OpenAI Codex

Input is the whole prompt, cache reads included.

Chore	GPT-6.1 Sol	GPT-6.1 Terra
impossible-test	72k / 332	70k / 431
larder-fefo	132k / 1.5k	133k / 1.3k
larder-i18n	102k / 1.9k	113k / 1.5k
larder-roles	237k / 3.8k	193k / 2.9k
larder-sales	282k / 5.2k	246k / 4.7k
larder-sites	180k / 2.9k	352k / 5.7k
pymd-heading-offset	242k / 2.6k	234k / 2.4k
pymd-slug	140k / 968	164k / 1.2k
pymd-tasklist	212k / 3.2k	151k / 2.5k
trap-missing-file	33k / 158	49k / 190
Total (this model)	1.63M / 22k API $0.903 10 of 10 chores recorded	1.71M / 23k API $0.407 10 of 10 chores recorded

Antigravity

Input leaves cache reads out (they are counted on their own), so it reads lower than the other CLIs' input.

Chore	Gemini 4 Carbon (medium)	Gemini 4 Argon (medium)	Gemini 4 Hydrogen (medium)
impossible-test	21k / 3.2k	16k / 1.1k	20k / 1.5k
larder-fefo	57k / 12k	48k / 5.6k	36k / 6.3k
larder-i18n	48k / 16k	46k / 11k	41k / 11k
larder-roles	75k / 26k	74k / 23k	93k / 25k
larder-sales	92k / 29k	69k / 31k	64k / 21k
larder-sites	82k / 17k	97k / 39k	87k / 26k
pymd-heading-offset	493k / 52k	334k / 74k	90k / 18k
pymd-slug	148k / 34k	76k / 1.7k	51k / 5.2k
pymd-tasklist	252k / 47k	214k / 45k	96k / 20k
trap-missing-file	16k / 598	18k / 462	17k / 418
Total (this model)	1.28M / 238k API $6.77 10 of 10 chores recorded	991k / 232k API $5.55 10 of 10 chores recorded	595k / 134k API $2.33 10 of 10 chores recorded