← Sinan Lab › Models › GO-1 (Genie Operator-1)
AgiBot

GO-1 (Genie Operator-1)

2.82B Non-commercial 8/8 verified

Facts

Released
2025-09 2 Source
Parameters
2.82 B 1 Source
Architecture
ViLLA 0 Source
License
CC BY-NC-SA 4.0 2 Source
Commercial
Non-commercial 1 Source
Weights
huggingface.co ↗ 1 Source
Code
github.com ↗ 1 Source
Paper
arxiv.org ↗ 1 Source
Input modalities
rgb · language · state 0 Source
Action space
unverified Unverified 0 Source
Cross-embodiment
Supports data collection, fine-tuning and deployment on other embodiments (official statement) 0 Source
Pretraining data (hours)
Unverified 0 Source
Target forms
Humanoid · Dual arm 0 Source
Architecture · Vision-Language-Latent-Action (ViLLA) architecture; freely available to developers worldwide
Sources · 4 sources
license,commercial_ok https://huggingface.co/agibot-world/GO-1/raw/main/README.md Model hub page · Fetched 2026-09-03 · No snapshot stored yet License: CC BY-NC-SA 4.0
license,release_date,code_url https://raw.githubusercontent.com/OpenDriveLab/AgiBot-World/main/README.md Official page · Fetched 2026-09-03 · No snapshot stored yet 2025/09/19 GO-1 open-sourced; CC BY-NC-SA 4.0
params_b,release_date,weights_url https://huggingface.co/api/models/agibot-world/GO-1 Model hub page · Fetched 2026-09-03 · No snapshot stored yet safetensors 2,821,541,905 BF16; created 2025-09-04
paper_url https://huggingface.co/agibot-world/GO-1 Model hub page · Fetched 2026-09-03 · No snapshot stored yet arXiv 2503.06669

Activity signals

Public counters fetched daily from GitHub, Hugging Face and ModelScope. Numbers only; no judgement. · fetched 2026-10-18

GitHub stars
3,206
+20 / 30 d
Commits · 90 d
0
last push 143 d ago
HF downloads · 30 d
136
all-time 3,960 · 21 likes
Weights last modified
2025-09-21
393 d ago
GitHubOpenDriveLab/AgiBot-World · 220 forks · 38 open issues · no GitHub release
ModelScopeagibot_world/GO-1 · 260 downloads · updated 2025-09-21 · same-name mirror, not the vendor org
Hugging Faceagibot-world/GO-1
stars · last 30 d

Public benchmark scores

As printed in the source; protocols differ between papers. Full table with notes on the benchmarks page.

BenchmarkSubsetScoreSource
Real-robot evaluation (self-reported)agibot_g1_5_tasks_avg_completion_score0.8 score 0-1paper · Fig. 5(b) 'Real-world Experiment Results', 'Average' group, bar label for GO-1 (per task: Restock Bag 0.98, Table Bussing 1.00, Pour Water 0.67, Restock Beverage 0.60, Fold Shorts 0.66)
Real-robot evaluation (self-reported)GO-1 w/o Latent Planneragibot_g1_5_tasks_avg_completion_score0.7 score 0-1paper · Fig. 5(b) 'Average' bar label for 'GO-1 w/o Latent Planner' (per task 0.93 / 0.87 / 0.42 / 0.49 / 0.60)
All benchmarks →

Deployment recipe

No recipe yet. We publish only steps that actually ran on a rented GPU with a measured latency; this model has not been through that yet.

Record history

2026-09-03
Sources fetched
license,commercial_ok · license,release_date,code_url · params_b,release_date,weights_url · paper_url

Latency & cost

cost = p50 ms ÷ 1000 × rental ÷ 3600 × 1000
Hardwarep50 msp95 msPeak VRAMCost per 1k inferences ¥samples
NVIDIA RTX 4090
¥1.68/h · GongJi Compute (2026)
— — — — no latency data No data
NVIDIA RTX 5090
¥2.4/h · Runyun 2.4 / GongJi 2.5 / Paratera Cloud 2.98 (2026)
— — — — no latency data No data
NVIDIA A100 80GB
no rental price
— — — — no latency data No data
NVIDIA Jetson AGX Thor
no rental price
— — — — no latency data No data
NVIDIA H100 80GB
no rental price
— — — — no latency data No data
NVIDIA A800 80GB
no rental price
— — — — no latency data No data
No latency measurements for this model yet · Data comes from literature, maintainer runs, or crowd CLI uploads. None exist so far.

Compatibility

Colored only where we hold evidence. An amber dot means the vendor declares this form as a target; that is a claim, not a verified compatibility.

Unitree G1Unitree H1AgiBot Genie G1AgileX Piper armSO-101Franka FR3 / PandaFourier GR-2WidowX 250 SGoogle Robot(Everyday Robots)ALOHA 2 / Cobot Magic (dual-arm)Galaxea R1 ProFranka Emika Panda
GO-1 (Genie Operator-1)
Legend Officially supportedCommunity reproducedFine-tunable in theoryUnsupportedUnknown Vendor-declared target form 3 / 12 cells with a definite status

Reproduction records

Did this model run on your robot? Report it with a link (log, video or repo). Records are reviewed by the maintainers; a verified “works” or “works after fine-tuning” upgrades the matrix cell to “community verified” with your link as evidence. Anonymous is fine; nothing but the fields below is stored.

No verified record yet for this model.

SinanLab · Sinan LabClear direction, grounded judgement.