Object-level Tasks on 3DCity-LLM 1.2M
30.64BLEU-43DCity-LLM
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| 3DCity-LLMTraining status=Training-required, Parameter scale=7B2026.03 | 30.64 | 42.81 | 48.89 | 7.33 | 6.02 | |
| Chat SceneTraining status=Training-required, Parameter scale=7B2026.03 | 28.67 | 41.87 | 47.82 | 7.17 | 5.86 | |
| City-VLMTraining status=Training-required, Parameter scale=7B2026.03 | 27.93 | 42.13 | 46.84 | 6.96 | 5.58 | |
| LLaVATraining status=Training-required, Parameter scale=7B2026.03 | 25.4 | 37.39 | 44.17 | 7 | 5.08 | |
| Chat 3DTraining status=Training-required, Parameter scale=7B2026.03 | 22.24 | 32.9 | 38.2 | 6.62 | 4.75 | |
| ChatGPT-5.1Training status=Training-free but payment-required, Parameter scale=>70B2026.03 | 17.72 | 29.01 | 33.95 | 7.92 | 6.5 | |
| DeepSeek-R1Training status=Training-free but payment-required, Parameter scale=>70B2026.03 | 15.6 | 24.2 | 37.44 | 7.48 | 6.17 | |
| Qwen3-VL MaxTraining status=Training-free but payment-required, Parameter scale=>70B2026.03 | 15.23 | 27.12 | 34.65 | 7.05 | 6.39 | |
| Gemini 3Training status=Training-free but payment-required, Parameter scale=>70B2026.03 | 14.94 | 25.02 | 33.87 | 7.45 | 6.47 |