GEN-1

Source-backed capabilities

• Operating environments: Elite Robots cobot validation workcell
• Control modes: Autonomous
• Material handling

  Demonstrated - 2026-07-21 - Stacked blocks in more than 1,800 autonomous runs without intervention. - environment: Elite Robots cobot validation workcell

  Source
• Packaging

  Demonstrated - 2026-07-21 - Folded boxes in more than 200 autonomous runs without intervention. - environment: Elite Robots cobot validation workcell

  Source

• Operating Milestone

  2,000+ runs - 2026-07-21 - Elite Robots - GEN-1 completed more than 1,800 block-stacking runs and 200 box-folding runs without intervention, with 99 percent reported task success.

  Source

• Towards Machines with a Thousand Hands

  2026-07-23 - Research Publication - Generalist reports that GEN-1 now supports a broad range of end effectors and demonstrates physical manipulation with extra-wide hands, a power screwdriver, tongs, a whisk, scraping tools and sweeping tools. The post frames the result as a single model conditioning on the current hand or tool and adapting contact strategy when the end effector changes.

  Source
• GEN-1: Scaling Embodied Foundation Models to Mastery

  2026-04-02 - Research Publication - Generalist introduces GEN-1 as a real-time multimodal robotics action model and reports repeated autonomous evaluations across six physical tasks. The release documents 99% average success on the selected tasks, faster execution than the compared prior models, and recovery behaviours under unexpected object configurations.

  Source

• Generalist releases GEN-1.5 with one-shot physical-task learning

  2026-08-19 - Research Publication - Across 10 tasks, Generalist reports 59% average success from one 3–12 second in-context demonstration and 83% after 10 gradient steps on five minutes of task data. The multimodal model maintains 30 seconds of video context alongside sensor, language and proprioceptive inputs, and produces action trajectories at 100 Hz. The release also shows prompts transferring from simulation to a physical robot and, in some cases, from human-hand demonstrations to immediate robot execution.

  Source
• Generalist reports up to 10–20× gains in GEN-1 actuator adaptation

  2026-08-04 - Research Publication - The update targets low-level adaptation to new actuators and robot embodiments rather than a new GEN-1 model release. Generalist reports gains of up to 10–20 times on internal benchmarks, without publishing the benchmark protocol or absolute scores. The company showed the improvement on high-precision disassembly of parts from a NIST board.

  Source
• Generalist AI validates GEN-1 on Elite Robots cobot platform

  2026-07-21 - Capability - The integration completed more than 1,800 autonomous block-stacking runs and 200 box-folding runs without intervention. The disclosed validation recorded 99% task success and execution about three times faster. GEN-1 itself debuted in April; the new event is the validated Elite Robots hardware integration.

  Source
• Generalist AI raises $400M at $2B valuation for robotics foundation models

  2026-06-04 - Funding - Generalist AI raised $400 million in funding at a $2 billion valuation including the new capital. Radical Ventures led the round, with participation from 8VC, Union Square Ventures, Hanabi Capital, Nvidia and Bezos Expeditions. The funding supports development of Generalist's robotics AI models, including GEN-1, for broader physical-task capability.

  Source
• Generalist AI releases GEN-1, a general-purpose robotics AI model achieving 99% success rates on physical tasks

  2026-04-02 - Product Launch - Generalist introduced GEN-1 as its latest milestone in scaling robot learning and positioned it as a general-purpose AI model for simple physical tasks. The company said GEN-1 reached 99 percent success rates on the showcased tasks, ran roughly 3 times faster, and adapted in real time to unexpected scenarios. Generalist also said the displayed results used only about one hour of robot data, presenting GEN-1 as a step down in task-specific data requirements.

  Source

Comparable Systems

• Being-H0.8

  BeingBeyond - Robotics Foundation Model

• Helix

  Figure AI - Robotics Foundation Model

• FusionMax

  Muks Robotics AI Pvt. Ltd. - Robotics Foundation Model

• GENE-26.5

  Genesis AI - Robotics Foundation Model

• Lumo 2

  Astribot - Robotics Foundation Model

• Rho-alpha

  Microsoft - Robotics Foundation Model

Related Systems

• DYNA-1

  Dyna Robotics - Robotics Foundation Model