Dual-Arm Sim
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
- October 2026
- Kind
- Simulated robots
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Strongest model tested
- Claude Fable 5.2 #1 on the capability index
- Last model added
- November 2026
- Scores refreshed
- November 12th, 2026
Claude Fable 5.2 leads with 59.8
Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.
- 1 Claude Fable 5.2 All four tasks 59.8
- 2 GPT-6 Astra All four tasks 49.5
- 3
Gemini 4 Argon All four tasks 49.5 - 4 GPT-6.1 Sol All four tasks 40.8
- 5 Gemini 3.8 Flash All four tasks 38.8
- 6 Claude Fable 5.1 All four tasks 37.8
- 7 Claude Sonnet 5.5 All four tasks 26.0
- 8 Claude Opus 5.5 All four tasks 19.0
- 9
Muse Wonder All four tasks 9.50 - 10 Gemini 3.1 Pro All four tasks 8.50
- 11 Grok 4.7 All four tasks 6.30
Source: Official Dual-Arm Sim leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 59.8 | All four tasks | Nov 2026 | Official leaderboard |
| 2 | GPT-6 Astra | 49.5 | All four tasks | Sep 2026 | Official leaderboard |
| 3 | Gemini 4 Argon | 49.5 | All four tasks | Sep 2026 | Official leaderboard |
| 4 | GPT-6.1 Sol | 40.8 | All four tasks | Sep 2026 | Official leaderboard |
| 5 | Gemini 3.8 Flash | 38.8 | All four tasks | Sep 2026 | Official leaderboard |
| 6 | Claude Fable 5.1 | 37.8 | All four tasks | Sep 2026 | Official leaderboard |
| 7 | Claude Sonnet 5.5 | 26.0 | All four tasks | Sep 2026 | Official leaderboard |
| 8 | Claude Opus 5.5 | 19.0 | All four tasks | Sep 2026 | Official leaderboard |
| 9 | Muse Wonder | 9.50 | All four tasks | Oct 2026 | Official leaderboard |
| 10 | Gemini 3.1 Pro | 8.50 | All four tasks | Feb 2026 | Official leaderboard |
| 11 | Grok 4.7 | 6.30 | All four tasks | Sep 2026 | Official leaderboard |
2 models have held number one on the official leaderboard since its release in October 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Dual-Arm Sim leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Dual-Arm Sim leaderboard
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More 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%
- 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 29%
- RoboLab In use Zero-shot DROID Franka policies in Isaac Lab on 120 tabletop tasks at three instruction levels, 10 episodes each. Success rate. FLUX 3 Action 42.9%
- 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%
- 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%