Benchmark Almanac

CRONOS

SpatialVLA 0.60 tops its leaderboard OpenVLA 0.56 leads the models we track
Not in model cards

Robot policies manipulate objects in simulation without resetting the entire scene after each attempt. The benchmark compares performance as the scene accumulates changes.

Made by
Po-Yi Wu and colleagues
Released
November 2026
Kind
Simulated robots
Level
Everyday
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Images, Text, Time series → Actions
Interaction
Agentic
Environment
A simulator
Items from
Generated
Refresh
One fixed set
Run by
Anyone
In views
Agents, Vision, Robotics
Last model added
June 2024
Scores refreshed
November 20th, 2026
2
Entries on its own leaderboard, 1 model we track

SpatialVLA tops the leaderboard with 0.60 OpenVLA leads with 0.56

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. For spatial generalization, the authors report no overall score. This is the plain mean of the two out-of-domain layout success rates. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is OpenVLA, at 0.56. This view shows only models we track, each at its best.

  1. 1 SpatialVLA Scene reset every 320 steps 0.60
  2. 2 OpenVLA Scene reset every 320 steps 0.56

Source: Official CRONOS leaderboard

Source: Official CRONOS leaderboard

#EntryScoreSettingDateSource
1 SpatialVLA 0.60 Scene reset every 320 steps Official leaderboard
2 OpenVLA 0.56 Scene reset every 320 steps Jun 2024 Official leaderboard
#ModelScoreSettingDateSource
1 OpenVLA 0.56 Scene reset every 320 steps Jun 2024 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard
0.52 0.54 0.56 2024 0.52 0.54 0.56 2024

Source: Official CRONOS leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Robotics

All 172 in Robotics
  • ERQA In use 400 multiple-choice visual questions from robot and egocentric footage on spatial, trajectory, action and state reasoning. Accuracy. Gemini Robotics ER 2 78.5%
  • SimplerEnv In use Real-to-sim replicas of Google Robot and WidowX/Bridge setups. Policies scored by success rate on pick, move, drawer and Bridge tasks. Praxis-1 80%
  • RoboLab In use Zero-shot DROID Franka policies in Isaac Lab on 120 tabletop tasks at three instruction levels, 10 episodes each. Success rate. Praxis-1 46.2%
  • RoboDojo In use Generalist manipulation policies run 42 Isaac Sim tasks and 18 remote real-robot tasks. Scored by task score and success rate. GPT-6 Astra 27.6%
  • Progress classification (Google DeepMind) In use Models assign each frame of a robot video to one of five task-progress bands from 0 to 100 percent. Scored by accuracy. Gemini Robotics ER 2 57.4%
  • Human proximity (Google DeepMind robotics) In use Models judge from robot camera views whether a human is within 1 meter, a spatial awareness check for safe robot behavior. Scored by accuracy. Gemini Robotics ER 2 93%

Data audit

7 of 8 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in June 2024, for OpenVLA. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 1 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (2 entries).
  • Note Models scored Only 1 model we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in June 2024, for OpenVLA.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on embodiedai-ntu.github.io: 2 rows for models we track and 1 other entry at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check