Benchmark Almanac

ATOM-Bench

π0.5 48.2%
Not in model cards

Robot policies combine manipulation skills on single arm and dual arm platforms.

The publisher reports model results.

Made by
BAAI FlagEval
Released
June 2026
Kind
Real robots
Level
Everyday
Scored
Settled by events
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images, Time series → Actions
Interaction
Agentic
Items from
Written by experts
Refresh
One fixed set
Run by
Anyone
In views
Agents, Vision, Robotics
Last model added
December 2025
Scores refreshed
November 20th, 2026
5
Entries on its own leaderboard, 2 models we track

π0.5 leads with 48.2% π0.5 leads with 48.2%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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. This view shows only models we track, each at its best.

  1. 1 π0.5 48.2%
  2. 2 Motus 34.4%
  3. 3 LingBot-VLA 23.8%
  4. 4 GR00T N1.6 23.6%
  5. 5 SmolVLA 7.43%

Source: Official ATOM-Bench leaderboard

Source: Official ATOM-Bench leaderboard

#EntryScoreSettingDateSource
1 π0.5 48.2% Apr 2025 Official leaderboard
2 Motus 34.4% Official leaderboard
3 LingBot-VLA 23.8% Official leaderboard
4 GR00T N1.6 23.6% Dec 2025 Official leaderboard
5 SmolVLA 7.43% Official leaderboard
#ModelScoreSettingDateSource
1 π0.5 48.2% Apr 2025 Official leaderboard
2 GR00T N1.6 23.6% Dec 2025 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% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) π0.5 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) π0.5

Source: Official ATOM-Bench 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 11 months ago, in December 2025, for GR00T N1.6. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (5 entries).
  • Pass Models scored 2 models we track, plus 3 other entries on its leaderboard.
  • Warning Newest score The newest came 11 months ago, in December 2025, for GR00T N1.6.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 48.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on flageval-baai.github.io: 2 rows for models we track and 3 other entries 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