Benchmark Almanac

Dual-Arm Sim

GPT-6 Astra 49.5 leads since Oct 2026 Not in model cards

Frontier models control a two-armed robot in a simulated operating room from cameras and sensors. Tasks include swapping instruments, replacing a drug cartridge and packing a surgical kit.

Ten models over 800 trials produced 11 task completions. Gemini 4 Argon ranked first with 9.

Made by micro1 Released Oct 2026 Simulated robots All tasks public Last model added Oct 2026 Scores refreshed 2 Nov 2026
Level
Expert Specialists with years of training, often over hours of work
Scored
Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers
Agent task Many steps in a terminal, browser, desktop, app, game or robot.
Paper Dataset Leaderboard
10
Models scored on its own leaderboard

2 models share the top score of 49.5

Best score per model from the benchmark's own leaderboard, read on 2 Nov 2026. Where a model ran with several settings or harnesses, we keep its best.

  1. 49.5 GPT-6 Astra
  2. 49.5 Gemini 4 Argon
  3. 40.8 GPT-6.1 Sol
  4. 38.8 Gemini 3.8 Flash
  5. 37.8 Claude Fable 5.1
  6. 26.0 Claude Sonnet 5.5
  7. 19.0 Claude Opus 5.5
  8. 9.50 Muse Wonder
  9. 8.50 Gemini 3.1 Pro
  10. 6.30 Grok 4.7
  1. 1 GPT-6 Astra 49.5
  2. 2 Gemini 4 Argon 49.5
  3. 3 GPT-6.1 Sol 40.8
  4. 4 Gemini 3.8 Flash 38.8
  5. 5 Claude Fable 5.1 37.8
  6. 6 Claude Sonnet 5.5 26.0
  7. 7 Claude Opus 5.5 19.0
  8. 8 Muse Wonder 9.50
  9. 9 Gemini 3.1 Pro 8.50
  10. 10 Grok 4.7 6.30
#ModelScoreSettingDateSource
1 GPT-6 Astra 49.5 Sep 2026 Official leaderboard
2 Gemini 4 Argon 49.5 Sep 2026 Official leaderboard
3 GPT-6.1 Sol 40.8 Sep 2026 Official leaderboard
4 Gemini 3.8 Flash 38.8 Sep 2026 Official leaderboard
5 Claude Fable 5.1 37.8 Sep 2026 Official leaderboard
6 Claude Sonnet 5.5 26.0 Sep 2026 Official leaderboard
7 Claude Opus 5.5 19.0 Sep 2026 Official leaderboard
8 Muse Wonder 9.50 Oct 2026 Official leaderboard
9 Gemini 3.1 Pro 8.50 Feb 2026 Official leaderboard
10 Grok 4.7 6.30 Sep 2026 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard 1 leader
GPT-6 Astra 49.5

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
0.00 10.0 20.0 30.0 40.0 50.0 2026 0.00 10.0 20.0 30.0 40.0 50.0 2026

No lab model card reports it yet

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.

More in Robotics

All 86 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%
  • RoboLab In use Zero-shot DROID Franka policies in Isaac Lab on 120 tabletop tasks at three instruction levels, 10 episodes each. Success rate. GR00T N1.7 8.58%
  • 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%
  • Moment finding (Google DeepMind) In use Models find the moment in a robot video when an event happens. Scored by accuracy and mean absolute time distance in seconds. Gemini Robotics ER 2 91.3%
  • 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%
  • LIBERO Fading Simulated Franka tabletop tasks in four 10-task suites. Policies fine-tuned on 50 demos per task. Success rate over ~50 trials. MolmoAct 2 97.2%