EmbodiedLab
Agents choose measurements, operate a simulated robot arm, and read instruments through cameras to complete 35 laboratory experiments.
- Made by
- Hongcheng Gao and colleagues
- Released
- October 2026
- Kind
- Simulated robots
- Level
- University
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- A simulator
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5.5 leads with 41.4% among models released by September 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6.1 Terra
- and 13 more
- 1 Claude Opus 5.5 Native control (T0), medium reasoning effort 41.4%
- 2 GPT-6 Astra Native control (T0), medium reasoning effort 35.7%
- 3 GPT-6.1 Sol Native control (T0), medium reasoning effort 25.7%
- 4 Kimi K3 Native control (T0), high reasoning effort 8.60%
- 5
DeepSeek V4.1 Flash Native control (T0), high reasoning effort 8.60%
- 6
Qwen 3.8 Max Native control (T0), high reasoning effort 2.90%
- 7 GLM-5.3-Flash Native control (T0), high reasoning effort 0%
Source: Official EmbodiedLab leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 41.4% | Native control (T0), medium reasoning effort | Sep 2026 | Official leaderboard |
| 2 | GPT-6 Astra | 35.7% | Native control (T0), medium reasoning effort | Sep 2026 | Official leaderboard |
| 3 | GPT-6.1 Sol | 25.7% | Native control (T0), medium reasoning effort | Sep 2026 | Official leaderboard |
| 4 | Kimi K3 | 8.60% | Native control (T0), high reasoning effort | Jul 2026 | Official leaderboard |
| 5 | | 8.60% | Native control (T0), high reasoning effort | Sep 2026 | Official leaderboard |
| 6 | | 2.90% | Native control (T0), high reasoning effort | Aug 2026 | Official leaderboard |
| 7 | GLM-5.3-Flash | 0% | Native control (T0), high reasoning effort | Aug 2026 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Determination, Basic and Advanced. Claude Opus 5.5 leads 3 of them, and GPT-6 Astra leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Determination
7 models we track have a score here.
- 1 Claude Opus 5.5 43.3%
- 2 GPT-6 Astra 40%
- 3 GPT-6.1 Sol 28.3%
- 4 Kimi K3 10%
- 5
DeepSeek V4.1 Flash 10%
- 6
Qwen 3.8 Max 3.30%
- 7 GLM-5.3-Flash 0%
Basic
7 models we track have a score here.
- 1 GPT-6 Astra ↑1 50%
- 2 Claude Opus 5.5 ↓1 38.9%
- 3 GPT-6.1 Sol 36.1%
- 4 Kimi K3 16.7%
- 5
DeepSeek V4.1 Flash 16.7%
- 6
Qwen 3.8 Max 5.60%
- 7 GLM-5.3-Flash 0%
Advanced
7 models we track have a score here.
- 1 Claude Opus 5.5 50%
- 2 GPT-6 Astra 25%
- 3 GPT-6.1 Sol 16.7%
- 4 Kimi K3 0%
- 5
Qwen 3.8 Max ↑1 0%
- 6 GLM-5.3-Flash ↑1 0%
- 7
DeepSeek V4.1 Flash ↓2 0%
Optimization
7 models we track have a score here.
- 1 Claude Opus 5.5 30%
- 2 GPT-6 Astra 10%
- 3 GPT-6.1 Sol 10%
- 4 Kimi K3 0%
- 5
Qwen 3.8 Max ↑1 0%
- 6 GLM-5.3-Flash ↑1 0%
- 7
DeepSeek V4.1 Flash ↓2 0%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official EmbodiedLab 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 EmbodiedLab 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
- 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
All 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (7 entries).
- Pass Models scored 7 models we track.
- Pass Newest score The newest is from September 2026, for GPT-6.1 Sol.
- Pass Frontier models 3 of the top 10 have a score, led by GPT-6 Astra (#4).
- Pass Headroom The best is 41.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 7 rows for models we track 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.