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 · tuning

2026-10-28 02:44 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/2026-10-28-0244derpmeter-daily-run on GitHub

Scores use the current grader. 0 votes were scored again from the raw results. 60 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

4.2Smart

S 11 · M 1 · D 0

Claude Sonnet 5.5

0.0Smart

S 12 · M 0 · D 0

GPT-6.1 Sol

0.0Smart

S 12 · M 0 · D 0

GPT-6.1 Terra

0.0Smart

S 12 · M 0 · D 0

Gemini 4 Argonmedium

41.7Meh

S 2 · M 10 · 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 Opus 5.5	+2.0%p	+0.0%p	12/12
Claude Sonnet 5.5	+1.0%p	+0.0%p	12/12
Whole run	—	+0.0%p
Used after the run	1%	80%

OpenAI CodexPlus

Model	5-hour	Weekly	Measured
GPT-6.1 Sol	+7.0%p	+1.0%p	12/12
GPT-6.1 Terra	+3.0%p	+0.0%p	12/12
Whole run	+10.0%p	+1.0%p
Used after the run	41%	36%

AntigravityPlan not reported

Model	5-hour	Weekly	Measured
Gemini 4 Argonmedium	+3.2%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
expiring-days	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
expiring-days	133k / 2.4k	96k / 1.3k
expiry-boundary	145k / 1.7k	94k / 933
fix-failing-test	95k / 932	119k / 960
generated-doc	71k / 720	70k / 529

What was not Smart

M
Claude Opus 5.5 · release-checklist · Too slow · 44s
44s over 40s
raw
M
Gemini 4 Argon · expiring-days · Too slow · 225s
225s over 70s
raw
M
Gemini 4 Argon · expiry-boundary · Too slow · 127s
127s over 50s
raw
M
Gemini 4 Argon · fix-failing-test · Too slow · 52s
52s over 35s
raw
M
Gemini 4 Argon · generated-doc · Too slow · 57s
57s over 35s
raw
M
Gemini 4 Argon · lint-only · Too slow · 42s
42s over 35s
raw

Whole run	+2.4%p	+0.7%p
Used after the run	8%	3%

expiry-boundary	S	S	S	S	MToo slow

fix-failing-test	S	S	S	S	MToo slow

generated-doc	S	S	S	S	MToo slow

impossible-test	S	S	S	S	S

lint-only	S	S	S	S	MToo slow

paginate-items	S	S	S	S	MToo slow

regression-fix	S	S	S	S	MToo slow

release-checklist	MToo slow	S	S	S	MToo slow

rename	S	S	S	S	MToo slow

stock-route	S	S	S	S	MToo slow

trap-missing-file	S	S	S	S	S

lint-only	141k / 1.1k	92k / 689

paginate-items	104k / 2.1k	73k / 1.1k

regression-fix	146k / 1.5k	122k / 1.3k

release-checklist	154k / 1.4k	100k / 964

rename	122k / 1.6k	96k / 1.2k

stock-route	99k / 2.0k	72k / 1.6k

trap-missing-file	68k / 370	68k / 328

Total (this model)	1.35M / 17k API $1.33 12 of 12 chores recorded	1.07M / 12k API $0.552 12 of 12 chores recorded

OpenAI Codex

Input is the whole prompt, cache reads included.

Chore	GPT-6.1 Sol	GPT-6.1 Terra
expiring-days	90k / 1.4k	89k / 1.2k
expiry-boundary	69k / 811	85k / 962
fix-failing-test	69k / 449	97k / 477
generated-doc	69k / 567	64k / 520
impossible-test	68k / 382	66k / 424
lint-only	67k / 302	83k / 287
paginate-items	90k / 1.3k	84k / 1.4k
regression-fix	106k / 852	87k / 631
release-checklist	85k / 589	87k / 553
rename	85k / 683	86k / 967
stock-route	72k / 1.3k	85k / 1.4k
trap-missing-file	47k / 181	49k / 215
Total (this model)	917k / 8.9k API $0.492 12 of 12 chores recorded	960k / 9.0k API $0.193 12 of 12 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)
expiring-days	42k / 12k
expiry-boundary	40k / 7.0k
fix-failing-test	28k / 1.2k
generated-doc	22k / 1.1k
impossible-test	21k / 385
lint-only	18k / 424
paginate-items	35k / 9.5k
regression-fix	26k / 2.0k
release-checklist	29k / 2.2k
rename	31k / 1.8k
stock-route	28k / 4.3k
trap-missing-file	13k / 256
Total (this model)	333k / 42k API $1.17 12 of 12 chores recorded