BesiegeField - Car - Hierarchical Design: leaderboard
Metric: Mean distance (m). Source: besiegefield.github.io. Saturation forecast: Around November 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 29.96 |
| 2 | O3 | 28.39 |
| 3 | DeepSeek V3 | 17.92 |
| 4 | Claude Opus 4 (20250514) | 14.56 |
| 5 | Qwen 3 Coder 480B A35B | 12.59 |
| 6 | Llama 4 Scout | 1.55 |
Interactive version: theaggregate.ai/benchmark?slug=besiegefield-car-hierarchical-design · How It Works · Data refreshed daily, snapshot 2026-10-09.