- RoboCasa, 24 tasks with the Panda Omron robot, average success rate, finetuned N1.7 checkpoint. N1.6 66.22% (examples/robocasa README) 70.8
- RoboCasa GR1 Tabletop Tasks, mean of 24 per-task success rates, 20 trials per task, finetuned N1.7 checkpoint (examples/robocasa-gr1-tabletop-tasks README) 44.5
- SimplerEnv Bridge (WidowX) average 62.3%. Fractal (Google robot) average 72.5%. N1.6 re-run 56.6% and 52.0% (examples/SimplerEnv README) 62.3
- RoboLab, zero-shot nvidia/GR00T-N1.7-DROID, 120 tasks, 40 episodes each, 412 of 4,800 successes. N1.6 reference 7.25% (examples/RoboLab README) 8.58
GR00T N1.7
GR00T N1.7 places in the top three on 2 benchmarks.
11
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
NVIDIA Apr 2026 GR00T N1.7
Open weights Flagship
No Epoch Capabilities Index score yet
- RoboColiseum 46.8% #7 /9
- RoboDojo-RC Tier 1 9.51% #9 /9
- VLA-Arena 52.5% #2 /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 | 52.5% | #2 of 8 | Official leaderboard | |
| RoboCasa | 70.8% | #1 of 4 | Lab model card | |
| Act2Answer | 68% | #1 of 3 | Official leaderboard | |
| PhAIL DROID: Everyday tasks | 62.3% | #3 of 6 | Official leaderboard | |
| SimplerEnv | 62.3% | #2 of 3 | Lab model card | |
| ArmnetBench | 29.4% | #3 of 4 | Official leaderboard | |
| LIBERO-MAX | 50% | #3 of 4 | Official leaderboard | |
| RoboColiseum | 46.8% | #7 of 9 | Official leaderboard | |
| RoboDojo-RC Tier 1 | 9.51% | #9 of 9 | Official leaderboard | |
| RoboCasa GR1 Tabletop Tasks | 44.5% | #4 of 4 | Lab model card | |
| RoboLab | 8.58% | #2 of 2 | Lab model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.