Mental Navigation on Video2Mental Overall
2.92Navigation Error (NE)NavMind-Stage1
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| NavMind-Stage1Rank=2, Category=Spatial Reasoning Models2026.03 | 2.92 | 48.2 | 37.1 | 34.3 | |
| NavMind-Stage2Rank=1, Category=Spatial Reasoning Models2026.03 | 2.92 | 48.8 | 38 | 35.2 | |
| Gemini-3-ProRank=6, Category=Proprietary Multimodal Large Language Models2026.03 | 4.73 | 8.3 | 3.9 | 3.2 | |
| Qwen3.5-397BRank=3, Category=Open-Source Multimodal Large Language Models2026.03 | 5.19 | 10.7 | 7.4 | 5.9 | |
| GPT-5.1Rank=4, Category=Proprietary Multimodal Large Language Models2026.03 | 5.28 | 10.3 | 0.6 | 5.2 | |
| Claude-Sonnet-4.6Rank=5, Category=Proprietary Multimodal Large Language Models2026.03 | 5.28 | 9.8 | 5.8 | 4.7 | |
| RynnBrain-8BRank=11, Category=Spatial Reasoning Models2026.03 | 6.13 | 0 | 0 | 0 | |
| Qwen3-VL-8BRank=7, Category=Open-Source Multimodal Large Language Models2026.03 | 6.45 | 4.4 | 4.4 | 4 | |
| InternVL-3.5-8BRank=10, Category=Open-Source Multimodal Large Language Models2026.03 | 6.64 | 0.9 | 1.6 | 1.4 | |
| Qwen3-VL-30BRank=8, Category=Open-Source Multimodal Large Language Models2026.03 | 6.9 | 4.3 | 5.2 | 4.4 | |
| Cambrian-SRank=9, Category=Spatial Reasoning Models2026.03 | 9.7 | 1.2 | 4.9 | 4.3 |