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 · 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 →
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 | 107k / 1.2k | 72k / 701 |
| larder-fefo | 207k / 5.7k | 162k / 1.5k |
| larder-i18n | 193k / 14k | 109k / 2.3k |
| larder-roles | 468k / 19k | 278k / 7.5k |
| larder-sales |
|---|
| 290k / 20k |
| 209k / 6.0k |
| larder-sites | 445k / 28k | 466k / 13k |
|---|
| pymd-heading-offset | 389k / 19k | 460k / 6.3k |
|---|
| pymd-slug | 151k / 5.3k | 151k / 2.0k |
|---|
| pymd-tasklist | 302k / 22k | 306k / 7.5k |
|---|
| trap-missing-file | 47k / 414 | 47k / 207 |
|---|
| Total (this model) | 2.60M / 135k API $5.45 10 of 10 chores recorded | 2.26M / 47k API $1.28 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 / 385 | 71k / 531 |
| larder-fefo | 131k / 1.3k | 134k / 1.3k |
| larder-i18n | 98k / 1.7k | 134k / 1.6k |
| larder-roles | 182k / 3.4k | 210k / 2.8k |
| larder-sales | 204k / 4.2k | 377k / 5.0k |
| larder-sites | 281k / 4.5k | 325k / 3.3k |
| pymd-heading-offset | 207k / 2.9k | 190k / 2.4k |
| pymd-slug | 125k / 910 | 135k / 904 |
| pymd-tasklist | 211k / 3.3k | 144k / 2.7k |
| trap-missing-file | 48k / 209 | 49k / 273 |
| Total (this model) | 1.55M / 23k API $0.937 10 of 10 chores recorded | 1.77M / 21k API $0.365 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 (high) |
|---|---|
| impossible-test | 14k / 1.1k |
| larder-fefo | 39k / 5.6k |
| larder-i18n | 46k / 13k |
| larder-roles | no record |
| larder-sales | no record |
| larder-sites | 115k / 45k |
| pymd-heading-offset | no record |
| pymd-slug | 90k / 4.0k |
| pymd-tasklist | 282k / 71k |
| trap-missing-file | 13k / 350 |
| Total (this model) | 601k / 140k API $3.78 7 of 10 chores recorded * |
* Some chores have no usage record (runs that hit the time limit before Nov 4 lost it to a runner bug; it is kept from Nov 4); the total leaves them out, so it reads low.