Robot makerDrivingSan Diego, CA, United States
Develops the open-source openpilot driver-assistance system and comma hardware, and trains openpilot driving policies inside a learned driving world model.
comma.ai develops openpilot, an MIT-licensed open-source driver-assistance system supporting more than 300 car models, and the comma four device, which it builds in San Diego. Its openpilot 0.11 release in March 2026 shipped a driving policy trained entirely on rollouts from a learned world model, a method described in its CVPR 2025 workshop paper. It publishes driving models and a 4B-parameter world model on Hugging Face.
Sources: comma.ai (19 Oct 2026) · github.com (19 Oct 2026) · blog.comma.ai (17 Mar 2026) · arxiv.org (27 Apr 2025) · huggingface.co (19 Oct 2026)
Private company
No funding rounds have been disclosed in sources we could verify.
#33 of 104 model companies · score 46.0 / 100 · updated 19 Oct 2026
Each bar shows an input from 0 to 100% before weighting. 2 of 2 listed models have open weights. Most-starred official repository: commaai/openpilot (63.9k stars, 19 Oct 2026).
The score (0–100) measures public, checkable evidence about a company's robot models. It does not measure private capability. A company that publishes no benchmark results and no weights can still have strong models. Every input is computed from the data on each company page, and every number there links to its source.
| Input | Weight | How it is measured |
|---|---|---|
| Published benchmarks | 35% | For each scored benchmark, the company's best result divided by the best result any company has published, averaged over the benchmarks it reports. No published results scores 0. Results come only from the model's own paper, model card or the official benchmark leaderboard. Scored: LIBERO (4-suite average success, %); SimplerEnv Google Robot, visual matching (%); SimplerEnv Google Robot, variant aggregation (%); SimplerEnv WidowX / Bridge (%); CALVIN ABC→D (average length, 0–5); RoboArena (pairwise rating). |
| Open weights | 20% | Share of the company's listed models whose weights the public can download. |
| Adoption | 20% | GitHub stars on the company's most-starred official model repository, on a log scale relative to the most-starred repository in the list. Hugging Face downloads are shown on company pages but not scored, because gated repositories report zero. |
| Released models | 15% | Number of publicly announced, named models, capped at 5. |
| Disclosed funding | 10% | The sum of the funding rounds listed on the company's profile that were disclosed in USD, on a log scale from $10M to the largest sum in the list. Rounds reported only in other currencies are listed but not converted or counted. This input applies only to private startups and robot makers. For big-tech divisions, research labs and listed companies it is n/a, and its weight is shared across the other inputs in proportion. |
Sources. arXiv papers and official model cards for benchmarks and parameters; official leaderboards (RoboArena); the GitHub and Hugging Face APIs for stars and downloads; company announcements and established press for funding. Missing values are shown as n/a, never estimated.
Updated 19 Oct 2026. Benchmark protocols differ between papers, for example in fine-tuning and number of trials, so small gaps between close scores are not meaningful.
Open weightsPolicy
openpilot 0.11 driving policy, a small transformer with 2 s of context at 5 fps, trained entirely on rollouts from comma's learned world model and shipped to openpilot users.
No benchmark results on a shared public benchmark have been published for this model.
Open weightsWorld model
Driving world model (video DiT with an inverse-dynamics plan head) that predicts paired-camera latents and a driving plan from frame history, future anchors and ego motion.
No benchmark results on a shared public benchmark have been published for this model.
