π0.5
π0.5 places in the top three on 4 benchmarks.
20
Benchmarks with a score
0
Ranked first, out of five or more models
4
In the top three
Physical Intelligence Apr 2025
π0.5
Open weights Flagship
No Epoch Capabilities Index score yet
- RoboDojo 11.4% #2 /6
- RoboLab 28.1% #2 /5
- RoboColiseum 57.4% #5 /9
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ArmnetBench | 47.6% | #1 of 4 | Official leaderboard | |
| PhAIL DROID: Everyday tasks | 62.5% | #2 of 6 | Official leaderboard | |
| RoboDojo | 11.4% | #2 of 6 | Official leaderboard | |
| LIBERO-PRO | 53% | #1 of 3 | Official leaderboard | |
| RoboArena | 1,608 | #1 of 3 | Official leaderboard | |
| RoboChallenge | 42.7% | #1 of 3 | Official leaderboard | |
| RoboLab | 28.1% | #2 of 5 | Official leaderboard | |
| LIBERO | 96.8% | #3 of 6 | Lab model card | |
| LIBERO-MAX | 65.7% | #2 of 4 | Official leaderboard | |
| PhAIL | 75.1% | #1 of 2 | Official leaderboard | |
| RoboTwin 2.0 | 58.3% | #1 of 2 | Official leaderboard | |
| SafeLIBERO | 57.8% | #1 of 2 | Official leaderboard | |
| RoboColiseum | 57.4% | #5 of 9 | Official leaderboard | |
| VLA-Arena | 44.3% | #5 of 8 | Official leaderboard | |
| RoboCasa365 | 16.9% | #3 of 4 | Official leaderboard | |
| LIBERO-Para | 71.4% | #1 of 1 | Official leaderboard | |
| RMBench | 10.4% | #1 of 1 | Official leaderboard | |
| RoboChallenge Table30 v2 | 0.73% | #1 of 1 | Official leaderboard | |
| RoboEval | 40.5% | #1 of 1 | Official leaderboard | |
| RoboMemArena | 21.5% | #1 of 1 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it.
Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better May 28, 2025