MolmoAct 2 (Ai2 blog) May 5, 2026
MolmoAct 2
MolmoAct 2 ranks first on 2 of the 5 benchmarks with five or more models scored.
10
Benchmarks with a score
2
Ranked first, out of five or more models
3
In the top three
MolmoAct 2
Open weights Flagship
No Epoch Capabilities Index score yet
- RoboDojo 8.99% #3 /6
- RoboDojo-RC Tier 1 18.9% #7 /9
- VLA-Arena 72.1% #1 /8
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 | |
|---|---|---|---|---|
| VLA-Arena | 72.1% | #1 of 8 | Official leaderboard | |
| LIBERO | 97.2% | #1 of 6 | Lab model card | |
| LIBERO-MAX | 66.9% | #1 of 4 | Official leaderboard | |
| RoboDojo | 8.99% | #3 of 6 | Official leaderboard | |
| RoboDojo-RC Tier 1 | 18.9% | #7 of 9 | Official leaderboard | |
| PhAIL DROID: Everyday tasks | 44.5% | #6 of 6 | Official leaderboard | |
| ArmnetBench | 18.9% | #4 of 4 | Official leaderboard | |
| Roboharm | 0% | #3 of 3 | Official leaderboard | |
| MolmoSpaces | 37.7% | #1 of 1 | Lab model card | |
| RoboEval | 44.3% | #1 of 1 | Lab model card |
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.
Capabilities
- MolmoSpaces 37.7
- LIBERO 97.2
- RoboEval 44.3