← Leaderboard
InternVLA-A1.5
VLAShanghai AI Lab · Jul 6, 2026 · built on InternVLA-A1
Successor to InternVLA-A1 that uses a frozen Wan2.2 video generator only during training, reported on LIBERO, LIBERO-Plus and SimplerEnv WidowX.
- Type
- VLA
- Parameters
- 2.7B
- Backbone
- Qwen3.5-2B
- Weights
- Open
- License
- CC-BY-NC-SA-4.0
- Commercial use
- Not allowed
- Released
- Jul 6, 2026
- Robots
- WidowX (Bridge), Franka Panda (sim), Aloha-AgileX (sim)
- SO-101
- –
- LeRobot
- –
Benchmark results
5 of 13 benchmarksRoboDojo (sim)Simulation
- Official leaderboard ↗Nov 3, 2026
#28 of 407.1%
LIBERO-PlusSimulation
- Paper / model card ↗Jul 2026
#9 of 2485.8%, self-reported by the authors, not a leaderboard entry
- 93.2%, self-reported by the authors, not a leaderboard entryPaper / model card ↗Jul 2026· self-reported, 50 clean + 500 randomized demos· n = 10000· non-standard
93.2%, self-reported by the authors, not a leaderboard entrynot ranked
- Paper / model card ↗Jul 2026
#10 of 4698.9%, self-reported by the authors, not a leaderboard entry
- Paper / model card ↗Jul 2026· visual matching
#6 of 1980.8%, self-reported by the authors, not a leaderboard entry
Not reported on 8 benchmarks
Robustness drop: 98.9% on LIBERO → 85.8% on LIBERO-Plus. The perturbed variants show how much of the LIBERO score is memorization.
Adoption
updated Nov 17, 2026Wrong or missing number? Report an error