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 →
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 |
|---|---|---|
| concurrent-ids | 123k / 1.8k | 123k / 1.8k |
| expiring-days | 105k / 2.6k | 97k / 1.5k |
| expiry-boundary | 145k / 1.8k | 95k / 1.6k |
| fix-failing-test | 121k / 1.4k | 119k / 871 |
| generated-doc | 70k / 652 | 69k / 495 |
|---|
| impossible-test | 71k / 899 | 70k / 534 |
|---|
| lint-only | 141k / 1.2k | 92k / 674 |
|---|
| paginate-items | 133k / 2.0k | 74k / 1.2k |
|---|
| regression-fix | 178k / 2.0k | 96k / 1.5k |
|---|
| release-checklist | 102k / 1.1k | 74k / 876 |
|---|
| rename | 124k / 1.4k | 150k / 2.4k |
|---|
| report-route | 101k / 1.8k | 97k / 1.5k |
|---|
| stock-route | 156k / 3.2k | 72k / 1.7k |
|---|
| tag-case | 95k / 1.2k | 94k / 956 |
|---|
| trap-missing-file | 69k / 383 | 69k / 394 |
|---|
| Total (this model) | 1.73M / 23k API $1.75 15 of 15 chores recorded | 1.39M / 18k API $0.744 15 of 15 chores recorded |
|---|
Input is the whole prompt, cache reads included.
| Chore | GPT-6.1 Sol | GPT-6.1 Terra |
|---|---|---|
| concurrent-ids | 85k / 974 | 107k / 986 |
| expiring-days | 89k / 1.5k | 87k / 1.2k |
| expiry-boundary | 69k / 762 | 86k / 727 |
| fix-failing-test | 69k / 449 | 103k / 464 |
| generated-doc | 86k / 541 | 50k / 439 |
| impossible-test | 71k / 352 | 86k / 374 |
| lint-only | 67k / 344 | 66k / 278 |
| paginate-items | 89k / 1.3k | 88k / 1.1k |
| regression-fix | 107k / 764 | 140k / 939 |
| release-checklist | 90k / 556 | 83k / 572 |
| rename | 71k / 781 | 89k / 758 |
| report-route | 87k / 1.4k | 90k / 1.3k |
| stock-route | 88k / 1.2k | 89k / 1.2k |
| tag-case | 69k / 676 | 85k / 501 |
| trap-missing-file | 49k / 149 | 49k / 285 |
| Total (this model) | 1.19M / 12k API $0.748 15 of 15 chores recorded | 1.30M / 11k API $0.253 15 of 15 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) |
|---|---|
| concurrent-ids | 26k / 1.7k |
| expiring-days | 44k / 14k |
| expiry-boundary | 34k / 6.8k |
| fix-failing-test | 20k / 989 |
| generated-doc | 30k / 1.1k |
| impossible-test | 21k / 1.1k |
| lint-only | 18k / 424 |
| paginate-items | 34k / 5.3k |
| regression-fix | 21k / 2.4k |
| release-checklist | 20k / 1.7k |
| rename | 29k / 5.8k |
| report-route | 39k / 7.9k |
| stock-route | 23k / 4.5k |
| tag-case | 34k / 1.8k |
| trap-missing-file | 13k / 348 |
| Total (this model) | 407k / 56k API $1.47 15 of 15 chores recorded |