Dual-Arm Sim Sample Transfer
Agents · 2026-10-30
Share of a model's 20 Dual-Arm Sim sample-transfer trials, one per seeded layout, in which the left arm picks up a sample bottle and hands it to the right arm in mid-air, under the task's arm-use rules, judged from simulator ground truth.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5.1 | 0.0 |
| Claude Opus 5.5 | 0.0 |
| Claude Sonnet 5.5 | 0.0 |
| Gemini 3.1 Pro Preview | 0.0 |
| Gemini 3.8 Flash | 0.0 |
| Gemini 4 Argon | 0.0 |
| GPT-6.1 Sol | 0.0 |
| GPT-6 Astra | 0.0 |
| Grok 4.7 | 0.0 |
| Muse Wonder | 0.0 |