← Leaderboard

EO-1

VLA
Shanghai AI Lab · Aug 28, 2025

Unified embodied foundation model trained with interleaved vision-text-action pretraining (Shanghai AI Lab with Fudan, AgiBot and NWPU), reported on LIBERO, SimplerEnv and several real robots including SO-100.

Type
VLA
Parameters
3B
Backbone
Qwen2.5-VL-3B
Weights
Open
License
MIT
Commercial use
Allowed
Released
Aug 28, 2025
Robots
Franka Panda (sim), WidowX (Bridge), AgiBot G-1, Franka Panda, WidowX 250 S, SO-100
SO-101
Yes
LeRobot
–

Benchmark results

2 of 13 benchmarks
LIBEROSaturatedSimulation
#22 of 4698.2%, self-reported by the authors, not a leaderboard entry
SimplerEnv WidowXSaturatedSimulation
#8 of 1972.7%, self-reported by the authors, not a leaderboard entry
Not reported on 11 benchmarks

Adoption

updated Nov 17, 2026
HF downloads · 30d
84
HF downloads · all time
2.8K
HF likes
15
GitHub stars
291
GitHub forks
27

Running the model

HardwarePrecisionConfigLatency / chunkStepsVRAMChunkControlSource
RTX 4090–multi-view inference–106 GB16–Aug 28, 2025 ↗

Trained on

Runs on

Wrong or missing number? Report an error