DROID: Everyday tasks · Franka FR3
Language-instructed tabletop tasks, each worded as a DROID annotation, on a Franka FR3 (DROID).
| # | Model | Episodes | Reliability @ 240 s | Speed @ 240 s |
|---|---|---|---|---|
| % of task done | tasks/min | |||
| Loading the benchmark… | ||||
Reliability is the percent of the task done within the time limit. Speed is successful tasks per minute. Models share a rank when chance can explain the difference. At 240 s the table shows the leaderboard, from the ranking model. Past 240 s only GPT-6 Astra, which ran with a 480 s limit, still moves. ± is half the 95% range.
In November 2026, the GR00T and π₀.₅ entries were updated, and GPT-6 Astra was added. Each ran one episode on 109 of the 286 tasks, drawn at random, beside two to four models from the earlier board. GR00T and π₀.₅ show only their November runs.
How reliable is it at each time limit?
The mean credit of how far the episodes had got within each time limit, with its 95% range. A success counts from its success mark, and a fail or a safety stop scores 0 from the end of its episode. An episode stopped early keeps how far it got. At 240 s the table shows the leaderboard's Reliability, from the ranking model, so there it can differ from this curve. Drag the marker to rank the table at another limit.
How far the episodes got
- Success
- At target
- Control
- Contact
- Reaching
- Floating
- Failed
- Safety stop
Each bar splits a model's episodes by how far they got: the verdict for a success, a fail or a safety stop, else the furthest stage marked in the current step. The number beside each stage is its credit for one step in Reliability.
More charts
When do the successes come?
The success marks of each model's episodes, smoothed, as a share of its episodes per second.
Is it faster, or more reliable?
Each line is a model at every time limit from 1 s to 480 s: its Speed in tasks/min across, its Reliability up. The dot is the current time limit, and the dashed lines are its 95% ranges. The axis ends at 6 tasks/min, so the quickest successes at a short limit fall beyond it.
Do two models really differ?
Episodes
Each episode and its own result, the newest first.