Mental Navigation on Video2Mental Long
3.77Navigation Error (NE)NavMind-Stage2
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| NavMind-Stage2Category=Spatial Reasoning Models2026.03 | 3.77 | 43.6 | 34.5 | 32.7 | |
| NavMind-Stage1Category=Spatial Reasoning Models2026.03 | 3.78 | 43.1 | 32.7 | 30.6 | |
| Gemini-3-ProCategory=Proprietary Multimodal Large Language Models2026.03 | 6.47 | 7.6 | 3.5 | 2.9 | |
| GPT-5.1Category=Proprietary Multimodal Large Language Models2026.03 | 6.66 | 6.2 | 4.4 | 3.9 | |
| Qwen3.5-397BCategory=Open-Source Multimodal Large Language Models2026.03 | 6.67 | 9.2 | 7.6 | 6.3 | |
| InternVL-3.5-8BCategory=Open-Source Multimodal Large Language Models2026.03 | 7.07 | 0.5 | 1.2 | 1 | |
| Claude-Sonnet-4.6Category=Proprietary Multimodal Large Language Models2026.03 | 7.17 | 4.4 | 5.9 | 5 | |
| Qwen3-VL-8BCategory=Open-Source Multimodal Large Language Models2026.03 | 8.18 | 3.5 | 2.9 | 2.7 | |
| Qwen3-VL-30BCategory=Open-Source Multimodal Large Language Models2026.03 | 8.64 | 3.2 | 5.5 | 5.1 | |
| RynnBrain-8BCategory=Spatial Reasoning Models2026.03 | 8.75 | 0 | 0 | 0 | |
| Cambrian-SCategory=Spatial Reasoning Models2026.03 | 9.72 | 1.3 | 5.4 | 4.6 |