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 · MODELS
Pick a model to see its score, time, tokens and API $ run by run, or add up to three to compare them on one chart. Up is worse on every chart.
+ adds a model to compare (up to 3).
Claude Code 2.1.326 · 5 runs · newest 2026-11-17 18:30 UTC →
| Model | This week | Week before | Votes | Most common reason | Avg time | Tokens in / out | Quota per run (5h · week) |
|---|---|---|---|---|---|---|---|
| Claude Fable 5.2 | 17.0 | — | 50 | Too slow · 15 | 99s | 358k / 9k | 1.50 · 0.14 pt |
| Claude Opus 5.5 | 16.2 | 17.9 | 71 | Too slow · 20 | 98s | 521k / 9k | 0.58 · 0.09 pt |
| Claude Sonnet 5.5 | 6.3 | 2.1 | 71 | Too slow · 7 | 63s | 304k / 6k | 0.38 · 0.04 pt |
| Model | This week | Week before | Votes | Most common reason | Avg time | Tokens in / out | Quota per run (5h · week) |
|---|---|---|---|---|---|---|---|
| GPT-6.1 Sol | 17.6 | 12.9 | 71 | Too slow · 18 | 76s | 248k / 3k | 1.35 · 0.21 pt |
CLI changes: 2.1.325 from 11-14 18h, 2.1.326 from 11-17 18h.
Larder
larder-fefolarder-i18nlarder-roleslarder-saleslarder-sitesPython-Markdown
pymd-heading-offsetpymd-slugPantry
toon-episode-copytoon-failed-charges| Run (UTC) | Score | S / M / D | Time per chore | Output / reasoning per chore | CLI |
|---|---|---|---|---|---|
| 2026-11-17 18:30 UTC | 13.6 | 8 / 3 / 0 | 142s · 8 overlapped | 14k / 3.3k | 2.1.326 (new) |
| 2026-11-16 18:30 UTC | 18.8 | 5 / 3 / 0 | 106s · 3 overlapped | 10k / 2.6k | 2.1.325 |
| 2026-11-15 18:30 UTC | 18.8 | 5 / 3 / 0 | 112s · 4 overlapped | 11k / 3.1k | 2.1.325 |
| 2026-11-14 18:30 UTC | 25.0 | 4 / 4 / 0 | 108s · 3 overlapped | 10k / 2.8k | 2.1.325 (new) |
| 2026-11-13 18:30 UTC | 25.0 | 4 / 4 / 0 | 110s · 5 overlapped | 10.0k / 3.1k | 2.1.323 |
| GPT-6.1 Terra | 12.7 | 9.3 | 71 | Too slow · 8 | 64s | 241k / 3k | 0.83 · 0.13 pt |
|---|
| Model | This week | Week before | Votes | Most common reason | Avg time | Tokens in / out | Quota per run (5h · week) |
|---|---|---|---|---|---|---|---|
| Gemini 4 Carbon (high) | 79.7 | — | 59 | Repeated mistake · 35 | 555s | 147k / 30k | 1.06 · 0.40 pt |
| Gemini 4 Argon (high) | 64.8 | 67.9 | 71 | Too slow · 36 | 451s | 136k / 29k | 1.14 · 0.62 pt |
| Gemini 4 Hydrogen (high) | 29.8 | — | 47 (+1 skipped) | Too slow · 17 | 167s | 62k / 14k | 0.39 · 0.20 pt |
pymd-tasklisttoon-image-fetch