RoboDojo Sim
We show this table for reference; we do not rank on it.
A simulated robotics benchmark that measures the average success rate of a model controlling robots across simulated manipulation tasks.
Benchmark score on RoboDojo Sim — November 11, 2026
We compile the RoboDojo Sim rows from provider self-reports. Claude Fable 5.2 leads the table at 64.9%, followed by Claude Opus 5.5 (39.4%) and Gemini 4 Argon (34.2%). We do not use these results to rank models overall.
Claude Fable 5.2
Anthropic
Claude Opus 5.5
Anthropic
Gemini 4 Argon
5 modelsAgenticCurrentDisplay onlyUpdated November 11, 2026
Benchmark score table (5 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Claude Fable 5.2Anthropic | 64.9% | Not reported | Closed |
| 2 | Claude Opus 5.5Anthropic | 39.4% | Not reported | Closed |
| 3 | Gemini 4 ArgonGoogle | 34.2% | Not reported | Closed |
| 4 | GPT-6 AstraOpenAI | 29.8% | Not reported | Closed |
| 5 | Claude Fable 5.1Anthropic | 27.6% | Not reported | Closed |
Among the reported RoboDojo Sim rows, Claude Fable 5.2 is first at 64.9%. The third row is 30.7 points behind. The broader top-10 range is 37.3 points, so the table still separates the published systems.
5 models have been evaluated on RoboDojo Sim. The benchmark falls in the Agentic category. RoboDojo Sim is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About RoboDojo Sim
Year
2026
Tasks
Simulated robot-control tasks (count not published)
Format
Average success rate
Difficulty
Embodied agent control
Anthropic's launch page reports RoboDojo Sim average success rates at each model's highest available effort, run internally by Anthropic (Gemini 4 Argon at high effort). The task set and harness are not public, so BenchLM keeps it display-only. First added from the Claude Fable 5.2 launch.
Freshness and provenance
Version
RoboDojo Sim 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does RoboDojo Sim measure?
A simulated robotics benchmark that measures the average success rate of a model controlling robots across simulated manipulation tasks.
Which model scores highest on RoboDojo Sim?
Claude Fable 5.2 by Anthropic currently leads with a score of 64.9% on RoboDojo Sim.
How many models are evaluated on RoboDojo Sim?
5 AI models have published results on RoboDojo Sim in the BenchLM catalog.
Compare top models on RoboDojo Sim
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.