Mental Navigation on Video2Mental Middle
2.45Navigation Error (NE)NavMind-Stage2
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| NavMind-Stage2Category=Spatial Reasoning Models2026.03 | 2.45 | 53.1 | 39.9 | 36.8 | |
| NavMind-Stage1Category=Spatial Reasoning Models2026.03 | 2.51 | 50.9 | 38.6 | 36 | |
| RynnBrain-8BCategory=Spatial Reasoning Models2026.03 | 3.75 | 0 | 0 | 0 | |
| Gemini-3-ProCategory=Proprietary Multimodal Large Language Models2026.03 | 3.97 | 8.6 | 4.1 | 3.5 | |
| Claude-Sonnet-4.6Category=Proprietary Multimodal Large Language Models2026.03 | 4.19 | 13.7 | 3.6 | 2.5 | |
| Qwen3.5-397BCategory=Open-Source Multimodal Large Language Models2026.03 | 4.32 | 10.3 | 7.4 | 6 | |
| GPT-5.1Category=Proprietary Multimodal Large Language Models2026.03 | 4.72 | 11.7 | 6.3 | 5.2 | |
| Qwen3-VL-8BCategory=Open-Source Multimodal Large Language Models2026.03 | 5.85 | 3.7 | 3.5 | 3.2 | |
| Qwen3-VL-30BCategory=Open-Source Multimodal Large Language Models2026.03 | 6.12 | 5.7 | 4.2 | 3.5 | |
| InternVL-3.5-8BCategory=Open-Source Multimodal Large Language Models2026.03 | 6.24 | 1.6 | 1.6 | 1.3 | |
| Cambrian-SCategory=Spatial Reasoning Models2026.03 | 10.04 | 0.3 | 4.1 | 3.7 |