Relationship-level Tasks on 3DCity-LLM 1.2M
20.98BLEU-43DCity-LLM
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| 3DCity-LLMTraining status=Training-required, Parameter scale=7B2026.03 | 20.98 | 34.61 | 42.09 | 5.13 | 4.36 | |
| City-VLMTraining status=Training-required, Parameter scale=7B2026.03 | 20.48 | 35.52 | 40.19 | 5.1 | 4.02 | |
| Qwen3-VL MaxTraining status=Training-free but payment-required, Parameter scale=>70B2026.03 | 18.99 | 32.7 | 40.69 | 6.3 | 5.37 | |
| Gemini 3Training status=Training-free but payment-required, Parameter scale=>70B2026.03 | 18.06 | 29.5 | 39.52 | 5.62 | 5.07 | |
| Chat SceneTraining status=Training-required, Parameter scale=7B2026.03 | 17.51 | 31.6 | 39.94 | 4.75 | 3.87 | |
| ChatGPT-5.1Training status=Training-free but payment-required, Parameter scale=>70B2026.03 | 16.64 | 30.11 | 38.42 | 6.08 | 4.95 | |
| DeepSeek-R1Training status=Training-free but payment-required, Parameter scale=>70B2026.03 | 14.09 | 27.04 | 37.91 | 5.75 | 4.28 | |
| LLaVATraining status=Training-required, Parameter scale=7B2026.03 | 13.98 | 27.66 | 33.92 | 4.33 | 3.51 | |
| Chat 3DTraining status=Training-required, Parameter scale=7B2026.03 | 13.71 | 25.11 | 34.42 | 4.8 | 3.02 |