Description Quality on Scene 3 Laboratory storage 1.0 (overall)
78Color AccuracySpatialMem
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SpatialMem2026.01 | 78 | 77 | 69 | |
| geminiModel=Google Gemini2026.01 | 72 | 77 | 63 | |
| internvl (Entry 1)Model=InternVL 2.5, Deployment=Local2026.01 | 70 | 75 | 61 | |
| llavaModel=LLaVA-Video, Deployment=Local2026.01 | 68 | 73 | 59 | |
| internvl (Entry 2)Model=InternVL 2.5, Deployment=Local2026.01 | 64 | 69 | 55 | |
| openaiModel=OpenAI GPT-4o2026.01 | 62 | 67 | 53 | |
| togetherModel=Qwen2.5-VL, Deployment=Cloud2026.01 | 57 | 62 | 49 | |
| qwen25vlModel=Qwen2.5-VL, Deployment=Local2026.01 | 52 | 57 | 44 |