derpmeterBETA

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 · COMPARE

Two runs, side by side

Pick a base run and a run to compare with it. Each model's change counts only the chores both runs can be compared on: same grader, same project and prompt. Lower is better.

BaseCompared withSwap

Per model

2026-10-28 18:30 UTC → 2026-10-28 00:39 UTC

These two runs share no chore scored by the same grader on the same inputs, so there is no change to show. Their own scores are below.

Model	Base	Compared	Change	Chores changed
Claude Opus 5.5	10.0	0.0	— over 0 chores	none
Claude Sonnet 5.5	5.0	0.0	— over 0 chores	none
GPT-6.1 Sol	5.0	—	— over 0 chores	none
GPT-6.1 Terra	5.0	—	— over 0 chores

Gemini 4 Argon (medium)	55.0	—	— over 0 chores	none

Chores × models

base → compared · outlined = changed · dashed = not compared

Chore	Opus 5.5	Sonnet 5.5	GPT-6.1 Sol	GPT-6.1 Terra	Gemini 4 Argon
Pantry
expiring-days	·S	·S	··	··	··
fix-failing-test	·S	·S	··	··	··
generated-doc	·S	·S	··	··	··
impossible-test	SS	SS	S·	S·	M·
lint-only	·S	·S	··	··	··
regression-fix	·S	·S	··	··	··
release-checklist	·S	·S	··	··	··
rename	·S	·S	··	··	··
stock-route	·S	·S	··	··	··
trap-missing-file	SS	SS	S·	S·	S·
Larder
larder-fefo	S·	S·	S·	S·	M·
larder-i18n	S·	S·	S·	S·	M
Python-Markdown
pymd-heading-offset	S·	S·	S·	S·	D·
pymd-slug	S·	S·	S·	S·

Pantry

expiring-days

Opus 5.5·SSonnet 5.5·SGPT-6.1 Sol··GPT-6.1 Terra··Gemini 4 Argon··

fix-failing-test

Opus 5.5·SSonnet 5.5·SGPT-6.1 Sol··GPT-6.1 Terra

Per model

What changed

Chores × models