Andon Labs

Category: Research & Academic

AI safety evaluation lab that tests agents on long-horizon, real-world tasks. Best known for Vending-Bench and embodied agent benchmarks that reveal how models behave when left to operate autonomously.

Open Andon Labs →

Tags

Andon Labs · AI safety evaluation · agent benchmarks · Vending-Bench · long horizon tasks · autonomy testing · Research & Academic · Simulation · Freemium · free tier · free trial

Similar AI tools in Research & Academic

• Zooniverse
• Humanitarian OpenStreetMap
• Ushahidi
• Open Notebook
• Cradle
• Lavo AI
• OpenRead
• Human or AI
• NVIDIA Cosmos
• GenCast
• Willow by Google
• GAIA by Microsoft