SidewalkBench - Queueing: leaderboard
Navigation policies drive a simulated delivery robot past a tight line of pedestrians across the sidewalk, in 100 procedurally generated sidewalk scenarios; the number is the success rate in percent, mean of 5 seeded runs. It isolates one pedestrian behaviour, where the long-route headline mixes them.
Metric: Success rate on 100 queueing pedestrian scenarios in procedurally generated scenes, mean of 5 seeded runs (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | FlowPilot | 32.4 | |
| 2 | S2E | 22.2 | |
| 3 | MBRA | 6 | |
| 4 | InternVLA-N1-DualVLN | 6 | |
| 5 | NoMaD | 4.4 | |
| 6 | MIMIC | 2.8 | |
| 7 | CityWalker | 1.4 | |
| 8 | ViNT | 0.2 |
Interactive version: theaggregate.ai/benchmark?slug=sidewalkbench-queueing · How It Works · Data refreshed daily, snapshot 2026-11-13.