Claude Code
Codex
Antigravity15.0Smart
LOADING COMMUNITY DATA
How derpy is your AI today?
LOADING COMMUNITY DATA
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.
DAILY RUN · daily
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 →
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 | +5.0%p | +0.0%p | 7/10 |
| Claude Sonnet 5.5 | +4.0%p | +0.0%p | 9/10 |
| Whole run | — | +1.0%p | |
| Used after the run | 1% | 79% |
OpenAI CodexPlus
| Model | 5-hour | Weekly | Measured |
|---|---|---|---|
| GPT-6.1 Sol | +12.0%p | +2.0%p | 10/10 |
| GPT-6.1 Terra | +7.0%p | +1.0%p | 10/10 |
| Whole run | +19.0%p | +3.0%p | |
| Used after the run | 19% | 100% |
AntigravityPlan not reported
| Model | 5-hour | Weekly | Measured |
|---|---|---|---|
| Gemini 4 Argonmedium | +2.1%p |
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.
Input is the whole prompt, cache reads and writes included.
| Chore | Claude Opus 5.5 | Claude Sonnet 5.5 |
|---|---|---|
| impossible-test | 73k / 687 | 72k / 434 |
| larder-fefo | 167k / 2.1k | 160k / 1.2k |
| larder-i18n | 140k / 2.8k | 108k / 2.0k |
| larder-roles | 760k / 14k | 293k / 7.6k |
Gemini 4 Argon · larder-roles · Repeated mistake · 435s
timed out at the hard cap (partial output kept)
Gemini 4 Argon · larder-sales · Repeated mistake · 563s
timed out at the hard cap (partial output kept)
Gemini 4 Argon · larder-sites · Repeated mistake · 611s
timed out at the hard cap (partial output kept)
Gemini 4 Argon · pymd-tasklist · Repeated mistake · 1203s
timed out at the hard cap (partial output kept)
Claude Opus 5.5 · larder-roles · Too slow · 136s
136s over 108s
Claude Opus 5.5 · larder-sales · Poor output · 105s
partly done: missed atomicStock, readme
| +1.3%p |
| 4/10 |
| Whole run | +17.4%p | +5.1%p | |
|---|---|---|---|
| Used after the run | 17% | 5% |
| trap-missing-file | S | S | S | S | S |
|---|
| Larder | |||||
|---|---|---|---|---|---|
| larder-fefo | S | S | MToo slow | S | MToo slow |
| larder-i18n | S | S | S | S | MToo slow |
| larder-roles | MToo slow | S | S | S | DRepeated mistake |
| larder-sales | MPoor output | S | MPoor output | MPoor output | DRepeated mistake |
| larder-sites | MToo slow | S | S | S | DRepeated mistake |
| Python-Markdown | |||||
|---|---|---|---|---|---|
| pymd-heading-offset | S | S | S | S | MToo slow |
| pymd-slug | S | S | S | S | S |
| pymd-tasklist | S | S | S | S | DRepeated mistake |
Pantry
trap-missing-fileLarder
Python-Markdown
pymd-heading-offsetpymd-slug| larder-sales |
|---|
| 477k / 11k |
| 448k / 8.4k |
| larder-sites | 877k / 19k | 888k / 18k |
|---|
| pymd-heading-offset | 696k / 11k | 340k / 5.4k |
|---|
| pymd-slug | 153k / 2.3k | 100k / 1.4k |
|---|
| pymd-tasklist | 514k / 10k | 225k / 7.4k |
|---|
| trap-missing-file | 71k / 398 | 47k / 227 |
|---|
| Total (this model) | 3.93M / 74k API $3.72 10 of 10 chores recorded | 2.68M / 52k API $1.42 10 of 10 chores recorded |
|---|
Input is the whole prompt, cache reads included.
| Chore | GPT-6.1 Sol | GPT-6.1 Terra |
|---|---|---|
| impossible-test | 68k / 339 | 82k / 361 |
| larder-fefo | 136k / 1.7k | 226k / 1.8k |
| larder-i18n | 117k / 1.7k | 129k / 1.7k |
| larder-roles | 214k / 3.6k | 226k / 2.7k |
| larder-sales | 184k / 4.3k | 192k / 3.5k |
| larder-sites | 241k / 3.4k | 291k / 2.9k |
| pymd-heading-offset | 203k / 2.8k | 199k / 2.6k |
| pymd-slug | 130k / 977 | 134k / 978 |
| pymd-tasklist | 147k / 2.8k | 177k / 2.9k |
| trap-missing-file | 47k / 199 | 46k / 174 |
| Total (this model) | 1.49M / 22k API $0.896 10 of 10 chores recorded | 1.70M / 20k API $0.357 10 of 10 chores recorded |
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 | 17k / 1.2k |
| larder-fefo | 38k / 5.2k |
| larder-i18n | 104k / 14k |
| larder-roles | 88k / 35k |
| larder-sales | 82k / 48k |
| larder-sites | 115k / 43k |
| pymd-heading-offset | 363k / 84k |
| pymd-slug | 79k / 3.8k |
| pymd-tasklist | 573k / 70k |
| trap-missing-file | 14k / 175 |
| Total (this model) | 1.47M / 304k API $7.55 10 of 10 chores recorded |
Claude Opus 5.5 · larder-sites · Too slow · 160s
160s over 152s
GPT-6.1 Sol · larder-fefo · Too slow · 39s
39s over 35s
GPT-6.1 Sol · larder-sales · Poor output · 78s
said done but admitted a gap: failed: tests
GPT-6.1 Terra · larder-sales · Poor output · 37s
said done but admitted a gap: failed: tests
Gemini 4 Argon · impossible-test · Too slow · 40s
40s over 25s
Gemini 4 Argon · larder-fefo · Too slow · 111s
111s over 35s
Gemini 4 Argon · larder-i18n · Too slow · 223s
223s over 53s
Gemini 4 Argon · pymd-heading-offset · Too slow · 1139s
1139s over 300s