LOADING COMMUNITY DATA
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 · tuning
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 | +2.0%p | +1.0%p | 5/5 |
| Claude Sonnet 5.5 | +1.0%p | +0.0%p | 5/5 |
| Whole run | +3.0%p | +1.0%p | |
| Used after the run | 17% | 82% |
OpenAI CodexPlus
| Model | 5-hour | Weekly | Measured |
|---|---|---|---|
| GPT-6.1 Sol | +6.0%p | +1.0%p | 5/5 |
| GPT-6.1 Terra | +3.0%p | +0.0%p | 5/5 |
| Whole run | — | +1.0%p | |
| Used after the run | 2% | 40% |
AntigravityPlan not reported
| Model | 5-hour | Weekly | Measured |
|---|---|---|---|
| Gemini 4 Argonmedium | +4.0%p |
| Chore | Claude Code | OpenAI Codex | Antigravity | ||
|---|---|---|---|---|---|
| Claude Opus 5.5 | Claude Sonnet 5.5 | GPT-6.1 Sol | GPT-6.1 Terra | Gemini 4 Argon | |
| Larder | |||||
| larder-cents | MPoor output | MPoor output | MPoor output | MPoor output | |
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 |
|---|---|---|
| larder-cents | 184k / 2.7k | 98k / 1.3k |
| larder-fefo | 136k / 2.4k | 126k / 1.2k |
| larder-i18n | 170k / 3.0k | 101k / 1.8k |
| larder-schema3 | 308k / 4.8k | 261k / 3.3k |
Claude Opus 5.5 · larder-cents · Poor output · 42s
partly done: missed qty
Claude Sonnet 5.5 · larder-cents · Poor output · 16s
partly done: missed qty
GPT-6.1 Sol · larder-cents · Poor output · 33s
partly done: missed qty
GPT-6.1 Sol · larder-transfer · Poor output · 44s
partly done: missed ledger
GPT-6.1 Terra · larder-cents · Poor output · 18s
partly done: missed qty
GPT-6.1 Terra · larder-transfer · Poor output · 29s
partly done: missed ledger
| +2.5%p |
| 3/5 |
| Whole run | — | +2.7%p | |
|---|---|---|---|
| Used after the run | 3% | 6% |
| larder-fefo | S | S | S | S | MToo slow |
|---|
| larder-i18n | S | S | S | S | MToo slow |
|---|
| larder-schema3 | S | S | S | S | MToo slow |
|---|
| larder-transfer | S | S | MPoor output | MPoor output | MToo slow |
|---|
Larder
larder-cents| larder-transfer |
|---|
| 164k / 5.5k |
| 241k / 3.5k |
| Total (this model) | 962k / 18k API $1.16 5 of 5 chores recorded | 827k / 11k API $0.439 5 of 5 chores recorded |
|---|
Input is the whole prompt, cache reads included.
| Chore | GPT-6.1 Sol | GPT-6.1 Terra |
|---|---|---|
| larder-cents | 116k / 1.2k | 104k / 1.1k |
| larder-fefo | 76k / 1.3k | 122k / 1.3k |
| larder-i18n | 117k / 2.0k | 131k / 1.9k |
| larder-schema3 | 172k / 2.2k | 128k / 1.8k |
| larder-transfer | 142k / 2.6k | 140k / 1.8k |
| Total (this model) | 624k / 9.4k API $0.402 5 of 5 chores recorded | 625k / 7.9k API $0.165 5 of 5 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) |
|---|---|
| larder-cents | 54k / 5.6k |
| larder-fefo | 46k / 7.1k |
| larder-i18n | 51k / 12k |
| larder-schema3 | 70k / 25k |
| larder-transfer | 67k / 23k |
| Total (this model) | 288k / 72k API $1.45 5 of 5 chores recorded |
Gemini 4 Argon · larder-cents · Poor output · 126s
partly done: missed qty
Gemini 4 Argon · larder-fefo · Too slow · 142s
142s over 120s
Gemini 4 Argon · larder-i18n · Too slow · 186s
186s over 150s
Gemini 4 Argon · larder-schema3 · Too slow · 324s
324s over 180s
Gemini 4 Argon · larder-transfer · Too slow · 296s
296s over 150s