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 · RUNS
Each run's votes and each model's score, with the change from that model's previous run. A change counts only chores both runs can be compared on: same grader, same project and prompt. Lower is better.
▲ dumber, ▼ smarter than the model's previous run in this list; hover a score for how many chores got a different vote. Every score uses the current grader. Amber tags are experiment changes starting at that run.
| Run (UTC) | Claude Code | OpenAI Codex | Antigravity | Links | ||
|---|---|---|---|---|---|---|
| Opus 5.5 | Sonnet 5.5 | Sol | Terra | Gemini 4 Argon | ||
| 2026-10-28 11:55 UTC | 0.0 not comparable | 0.0 not comparable | 0.0 not comparable | 0.0 not comparable | 83.3 not comparable | vs previous →raw |
| 2026-10-28 06:58 UTC 15 not comparable | 16.7 not comparable | 33.3 not comparable | 50.0 not comparable | 16.7 not comparable | 83.3 not comparable | vs previous →raw |
| 2026-10-28 06:14 UTC | 50.0 not comparable | 0.0 not comparable | 16.7 not comparable | 16.7 not comparable | 83.3 not comparable | vs previous →raw |
| 2026-10-28 05:09 UTC 25 not comparable | 10.0 not comparable | 10.0 not comparable | 20.0 not comparable | 20.0 not comparable | 50.0 not comparable | vs previous →raw |
| 2026-10-28 03:35 UTC 15 not comparable | 0.0 not comparable | 0.0 not comparable | 0.0 not comparable | 33.3 not comparable | 50.0 not comparable | vs previous →raw |
| 2026-10-28 03:06 UTC 75 not comparable | 0.0 not comparable | 0.0 not comparable | 6.7 not comparable | 0.0 not comparable | 50.0 not comparable | vs previous →raw |
| 2026-10-28 02:44 UTC 60 not comparable | 4.2 not comparable | 0.0 not comparable | 0.0 not comparable | 0.0 not comparable | 41.7 not comparable | vs previous →raw |
| 2026-10-28 02:25 UTC 60 not comparable | 0.0 first run | 0.0 first run | 0.0 first run | 0.0 first run | 45.8 first run | raw |
The chores of the newest run (2026-10-28 11:55 UTC) over the last 8 runs, oldest on the left; times are UTC. Open a column for that run.
pymd-slugpymd-tasklist