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 03:35 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/2026-10-28-0335derpmeter-daily-run on GitHub

Scores use the current grader. 0 votes were scored again from the raw results. 15 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

0.0Smart

S 3 · M 0 · D 0

Claude Sonnet 5.5

0.0Smart

S 3 · M 0 · D 0

GPT-6.1 Sol

0.0Smart

S 3 · M 0 · D 0

GPT-6.1 Terra

33.3Smart

S 2 · M 0 · D 1

Gemini 4 Argonmedium

50.0Meh

S 0 · M 3 · 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	+0.0%p	+0.0%p	3/3
Claude Sonnet 5.5	+1.0%p	+0.0%p	3/3
Whole run	+1.0%p	+0.0%p
Used after the run	10%	81%

OpenAI CodexPlus

Model	5-hour	Weekly	Measured
GPT-6.1 Sol	+2.0%p	+1.0%p	3/3
GPT-6.1 Terra	+1.0%p	+0.0%p	3/3
Whole run	+3.0%p	+1.0%p
Used after the run	57%	39%

AntigravityPlan not reported

Model	5-hour	Weekly	Measured
Gemini 4 Argonmedium	+1.5%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
add-validation	S	S	S	DHallucination

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
add-validation	134k / 2.7k	124k / 2.3k
remove-item	98k / 1.7k	124k / 1.9k
use-stock	121k / 1.6k	96k / 1.0k
Total (this model)	353k / 6.1k API $0.395 3 of 3 chores recorded	344k / 5.2k API $0.177

What was not Smart

D
GPT-6.1 Terra · add-validation · Hallucination · 21s
claimed success: failed: tests
raw
M
Gemini 4 Argon · add-validation · Too slow · 210s
210s over 40s
raw
M
Gemini 4 Argon · remove-item · Too slow · 212s
212s over 35s
raw
M
Gemini 4 Argon · use-stock · Too slow · 97s
97s over 35s
raw

Whole run	+1.3%p	+0.4%p
Used after the run	12%	4%

remove-item	S	S	S	S	MToo slow

use-stock	S	S	S	S	MToo slow

OpenAI Codex

Input is the whole prompt, cache reads included.

Chore	GPT-6.1 Sol	GPT-6.1 Terra
add-validation	110k / 1.6k	115k / 1.4k
remove-item	67k / 1.1k	87k / 960
use-stock	70k / 789	83k / 1.0k
Total (this model)	247k / 3.5k API $0.175 3 of 3 chores recorded	284k / 3.4k API $0.071 3 of 3 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)
add-validation	40k / 9.2k
remove-item	37k / 7.7k
use-stock	34k / 3.1k
Total (this model)	111k / 20k API $0.459 3 of 3 chores recorded