GPT-6-Astra evaluated on EBench for direct and policy-harness robot control
Direct control leads on short tasks but lags on long-horizon work; calling a VLA or WAM matches top policies at lower token cost.
46
Organization
InternRobotics
- Mentions · 7d1
- Mentions · 30d1
- All mentions2
- First seenSep 24, 2026
- Last mentioned4d ago
Timeline
2 articles · newest firstInternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data
InternW0-Δ is a world action model pretrained on over 20,000 hours of open robot and human data.
58
Appears with
- GPT-6-Astraai model · 1
- EBenchproduct · 1
- InternW0-Δai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.