Model comparison
act_so101_keyboard_gray_cube_clean11 vs o3
Capability radar, value bars, and side-by-side posture.
act_so101_keyboard_gray_cube_clean11
Not scored
value score
o3
93
value score
act_so101_keyboard_gray_cube_clean11 ctx
—
o3 ctx
200K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- o393
Attribute tape
| Field | act_so101_keyboard_gray_cube_clean11 | o3 |
|---|---|---|
| Developer | Timmy | OpenAI |
| Context | — | 200K |
| Modalities | Text, Code | |
| Openness | — | Proprietary Model |
| Speed | — | — |
| Price | — | $10/1M in · $40/1M out |
| Value score | — | 93 |
| Summary | A task-specific ACT (Action Chunking with Transformers) imitation-learning policy checkpoint for the SO-101 robotic arm, trained via the Hugging Face LeRobot stack to perform a tabletop keyboard/gray-cube manipulation task. It outputs chunked action sequences from sensory input to control the arm through the learned cleaning behavior. | OpenAI reasoning model focused on hard problems. |