Galahad
Galahad repaired policy (checkpoint undisclosed) 97.7% tops its leaderboard
Not in model cards Vision-language-action policies are tested on whether they follow instructions. One word of the instruction changes and the policy must change its behavior.
A base policy finished 89 of 200 LIBERO object trials with the instruction replaced by xxx. The repo also ships fixed demonstration generators.
- Made by
- phi-monster (Galahad authors)
- Released
- July 2026
- Kind
- Simulated robots
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
2
Entries on its own leaderboard, 0 models we track
Galahad repaired policy (checkpoint undisclosed) tops the leaderboard with 97.7%
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 Galahad repaired policy (checkpoint undisclosed) deconfounded demonstrations; rank-32 update; named-object reach 97.7%
- 2 Galahad base policy (checkpoint undisclosed) counterfactual battery; named-object reach 35.6%
Source: Official Galahad leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Galahad repaired policy (checkpoint undisclosed) | 97.7% | deconfounded demonstrations; rank-32 update; named-object reach | Official leaderboard | |
| 2 | Galahad base policy (checkpoint undisclosed) | 35.6% | counterfactual battery; named-object reach | 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%