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

2026-11-02 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/2026-11-02-1830derpmeter-daily-run on GitHub

Scores use the current grader. 0 votes were scored again from the raw results. 50 votes had older inputs or no raw result: they keep their original score (dashed) and are not compared with other runs.

Claude Opus 5.5

10.0Smart

S 8 · M 2 · D 0

Claude Sonnet 5.5

5.0Smart

S 9 · M 1 · D 0

GPT-6.1 Sol

5.0Smart

S 9 · M 1 · D 0

GPT-6.1 Terra

5.0Smart

S 9 · M 1 · D 0

Gemini 4 Argonmedium

55.0Meh

S 2 · M 5 · D 3

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 Opus 5.5	+1.0%p	+0.0%p	5/10
Claude Sonnet 5.5	+3.0%p	+0.0%p	8/10
Whole run	+14.0%p	+1.0%p
Used after the run	17%	61%

OpenAI CodexPlus

Model	5-hour	Weekly	Measured
GPT-6.1 Sol	+12.0%p	+1.0%p	10/10
GPT-6.1 Terra	+7.0%p	+1.0%p	10/10
Whole run	+19.0%p	+2.0%p
Used after the run	27%	95%

AntigravityPlan not reported

Model	5-hour	Weekly	Measured
Gemini 4 Argonmedium	+2.6%p

Chores × models

S Smart · M Meh · D Dumb · – skipped

Chore	Claude Code		OpenAI Codex		Antigravity
Chore	Claude Opus 5.5	Claude Sonnet 5.5	GPT-6.1 Sol	GPT-6.1 Terra	Gemini 4 Argon
Pantry
impossible-test	S	S	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 Opus 5.5	Claude Sonnet 5.5
impossible-test	73k / 901	72k / 655
larder-fefo	136k / 1.8k	191k / 1.8k
larder-i18n	210k / 4.2k	110k / 2.5k
larder-roles	542k / 12k	247k / 7.0k

What was not Smart

D
Gemini 4 Argon · larder-roles · Repeated mistake · 435s
stuck past the hard cap
raw
D
Gemini 4 Argon · larder-sales · Repeated mistake · 563s
stuck past the hard cap
raw
D
Gemini 4 Argon · pymd-heading-offset · Repeated mistake · 1204s
stuck past the hard cap
raw
M
Claude Opus 5.5 · larder-roles · Too slow · 115s
115s over 108s
raw
M
Claude Opus 5.5 · larder-sites · Too slow · 227s
227s over 152s
raw
M
Claude Sonnet 5.5 · larder-sales · Poor output · 60s
said done but admitted a gap: missed atomicStock
raw

Whole run	+15.7%p	+5.6%p
Used after the run	16%	38%

trap-missing-file	S	S	S	S	MToo slow

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

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

larder-sites	1.32M / 25k	808k / 14k

pymd-heading-offset	824k / 12k	386k / 6.0k

pymd-slug	179k / 2.2k	99k / 1.4k

pymd-tasklist	589k / 11k	310k / 7.2k

trap-missing-file	70k / 513	47k / 208

Total (this model)	4.32M / 79k API $4.03 10 of 10 chores recorded	2.53M / 48k API $1.35 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	71k / 379	71k / 425
larder-fefo	143k / 1.5k	151k / 1.5k
larder-i18n	117k / 2.1k	129k / 1.5k
larder-roles	243k / 4.3k	209k / 2.8k
larder-sales	227k / 4.3k	217k / 4.4k
larder-sites	204k / 3.4k	300k / 4.5k
pymd-heading-offset	183k / 2.8k	184k / 2.3k
pymd-slug	143k / 1.1k	121k / 1.0k
pymd-tasklist	152k / 3.1k	155k / 2.6k
trap-missing-file	33k / 171	32k / 168
Total (this model)	1.52M / 23k API $0.869 10 of 10 chores recorded	1.57M / 21k API $0.417 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 Argon (medium)
impossible-test	15k / 946
larder-fefo	52k / 7.3k
larder-i18n	47k / 13k
larder-roles	no record
larder-sales	no record
larder-sites	111k / 44k
pymd-heading-offset	no record
pymd-slug	91k / 4.0k
pymd-tasklist	284k / 71k
trap-missing-file	16k / 378
Total (this model)	617k / 141k API $3.78 7 of 10 chores recorded *

* Some chores have no usage record (runs that hit the time limit before Nov 4 lost it to a runner bug; it is kept from Nov 4); the total leaves them out, so it reads low.