FlashDexRetarget 50-motion benchmark
Retarget 50 human hand-object motions (HOT3D, TACO, OakInk2) to XHand and Sharpa hands in Isaac Sim. Scored by object pose-error success thresholds.
Method paper with its own test set. Reports compute and success together: 0.90 success with 29 GPU-hours versus CHORD's 0.46 with 2,847. Failed baseline runs count toward compute.
- Made by
- KAIST AI + Holiday Robotics
- Released
- October 2026
- Kind
- Simulated robots
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
FlashDexRetarget tops the leaderboard with 90%
Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 1 FlashDexRetarget (a) XHand; Multi motion 90%
- 2 Do as I Do (b) Sharpa Wave Hand; Single motion 64%
- 3 CHORD (b) Sharpa Wave Hand; Single motion 50%
- 4 DexMachina (a) XHand; Single motion 48%
Source: Official FlashDexRetarget 50-motion benchmark leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | FlashDexRetarget | 90% | (a) XHand; Multi motion | Official leaderboard | |
| 2 | Do as I Do | 64% | (b) Sharpa Wave Hand; Single motion | Official leaderboard | |
| 3 | CHORD | 50% | (b) Sharpa Wave Hand; Single motion | Official leaderboard | |
| 4 | DexMachina | 48% | (a) XHand; Single motion | Official leaderboard |
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More in Robotics
- ERQA In use 400 multiple-choice visual questions from robot and egocentric footage on spatial, trajectory, action and state reasoning. Accuracy.
Gemini Robotics ER 2 78.5% - RoboDojo In use Generalist manipulation policies run 42 Isaac Sim tasks and 18 remote real-robot tasks. Scored by task score and success rate. GPT-6 Astra 29%
- RoboLab In use Zero-shot DROID Franka policies in Isaac Lab on 120 tabletop tasks at three instruction levels, 10 episodes each. Success rate. FLUX 3 Action 42.9%
- Progress classification (Google DeepMind) In use Models assign each frame of a robot video to one of five task-progress bands from 0 to 100 percent. Scored by accuracy. Gemini Robotics ER 2 57.4%
- Human proximity (Google DeepMind robotics) In use Models judge from robot camera views whether a human is within 1 meter, a spatial awareness check for safe robot behavior. Scored by accuracy. Gemini Robotics ER 2 93%
- Moment finding (Google DeepMind) In use Models find the moment in a robot video when an event happens. Scored by accuracy and mean absolute time distance in seconds. Gemini Robotics ER 2 91.3%