All topicsSTATE OF AI REPORT.

What was RT-2?

RT-2 was a vision-language-action approach that represented robot actions as tokens and trained jointly on web-derived knowledge and robot data, allowing semantic knowledge to inform manipulation.

What was RT-2? - 2023 report, slide 45
What was RT-2?. 2023 report, slide 45 (PDF page 45)

How to read this finding

RT-2 specifications and Swift racing outcomes describe different systems. Racing performance does not establish general robotics capability, and inference frequency is not a success rate for manipulation tasks.

Read the full Robotics section

Evidence you can use

Robotics in the 2023 report

Historical snapshot: October 2023. Dates and populations are specified per row.

Robotics in the 2023 report
MeasureReported valueDefinition and source
Largest RT-2 model55B parametersLargest vision-language-action model described in the report.2023 report, slide 45 (PDF page 45)
RT-2 control frequency1-3 HzReported inference frequency for the largest model served through a multi-TPU cloud system.2023 report, slide 45 (PDF page 45)
Swift human opponents3 championsHuman champions in the reported drone-racing comparison; Swift won several races.2023 report, slide 47 (PDF page 47)

RT-2 specifications and Swift racing outcomes describe different systems. Racing performance does not establish general robotics capability, and inference frequency is not a success rate for manipulation tasks.

Sources and dates

Historical snapshot published October 12, 2023. This web edition was prepared on October 10, 2026 from the online deck and original launch posts. Findings and forecasts retain their original time frame.

  1. 2023 report, slide 45 (PDF page 45)Original 2023 report. Printed slide numbers match PDF page numbers in this edition.
  2. 2023 report, slide 47 (PDF page 47)Original 2023 report. Printed slide numbers match PDF page numbers in this edition.
  3. State of AI Report 2023: online slides
  4. Nathan Benaich: The State of AI Report 2023Air Street Press, October 12, 2023.
  5. Welcome to State of AI Report 2023Original website launch post, October 12, 2023.

Cite this page

Benaich, Nathan. “What was RT-2?.” State of AI Report 2023. Historical report snapshot; web edition prepared 2026-10-10.