BesiegeField - Car - Single-agent: 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 | 33.96 |
| 2 | O3 | 15.28 |
| 3 | Claude Opus 4 (20250514) | 9.83 |
| 4 | DeepSeek V3 | 9.06 |
| 5 | Qwen 3 Coder 480B A35B | 8.87 |
| 6 | Llama 4 Scout | 0.02 |
Interactive version: theaggregate.ai/benchmark?slug=besiegefield-car-single-agent · How It Works · Data refreshed daily, snapshot 2026-10-09.