SurgVLA-Bench - Level 2 Vessel Clipping: leaderboard
Placing a hemostatic clip on the designated segment of a vessel among several candidate sites in the SurRoL laparoscopic simulator, a conditional task of SurgVLA-Bench (Sun et al., 2026). Models are LoRA fine-tuned on the Level 2 demonstrations; binary success rate in percent over 50 trials with a 100-step limit; higher is better.
Metric: Success rate (%; T2-3 clip placement on a designated vessel segment, SurgVLA-Bench Level 2, 50 trials in the SurRoL laparoscopic simulator with a 100-step limit; LoRA fine-tuned on the level's demonstrations). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | OpenVLA | 72 | |
| 2 | π0.5 | 14 | |
| 3 | SmolVLA | 10 | |
| 4 | π0 | 6 |
Interactive version: theaggregate.ai/benchmark?slug=surgvla-bench-level-2-vessel-clipping · How It Works · Data refreshed daily, snapshot 2026-11-12.