VehicleArena - Multi-Agent Cabin: leaderboard

Metric: Score (0-100). Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.

Top models

#ModelScoreOverall rank
1GPT-5.6 Sol (High)94#18 (GPT-5.6 Sol)
2DeepSeek V4.1 Flash (Max)73.9#35 (DeepSeek V4.1 Flash)
3Qwen 3.8 Max (xHigh)65.4#28 (Qwen 3.8 Max)
4GLM-5.3 Flash (Max)63.1#62 (GLM-5.3 Flash)
5Qwen 3.8 27B (xHigh)54.5#95 (Qwen 3.8 27B)
6Kimi K3 (Max)49.2#27 (Kimi K3)
7Qwen 3 VL 32B Instruct31.8#278
8Qwen 3 VL 8B Instruct7#406

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #8 Claude Fable 5.1.

Interactive version: theaggregate.ai/benchmark?slug=vehiclearena-multi-agent-cabin · How It Works · Data refreshed daily, snapshot 2026-10-13.