Video Captioning on Video Detail Caption (VDC)
36.49Throughput (Tokens/s)LVSPEC
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| LVSPECModel=Qwen2.5-VL, Setting=Self-SD2026.04 | 36.49 | 8.36 | 1.77 | |
| LVSPECModel=LLaVA-OV, Setting=Self-SD2026.04 | 36.4 | 8.46 | 1.38 | |
| SPECVLMModel=LLaVA-OV, Setting=Self-SD2026.04 | 35.46 | 3.91 | 1.34 | |
| FLY⊖Model=Qwen2.5-VL, Setting=Self-SD2026.04 | 32.24 | 6.86 | 1.56 | |
| FLY⊖Model=LLaVA-OV, Setting=Self-SD2026.04 | 31.72 | 6.83 | 1.2 | |
| SPECVLMModel=Qwen2.5-VL, Setting=Self-SD2026.04 | 31.45 | 3.85 | 1.53 | |
| FLYModel=LLaVA-OV, Setting=Self-SD2026.04 | 29.39 | 6.23 | 1.11 | |
| FLYModel=Qwen2.5-VL, Setting=Self-SD2026.04 | 28.16 | 6.53 | 1.37 | |
| AutoregressiveModel=LLaVA-OV, Setting=Self-SD2026.04 | 26.45 | — | 1 | |
| NAIVE SDModel=LLaVA-OV, Setting=Self-SD2026.04 | 23.83 | 4.58 | 0.9 | |
| LVSPECModel=Qwen2.5-VL, Setting=Std.-SD2026.04 | 21.47 | 7.76 | 2.7 | |
| AutoregressiveModel=Qwen2.5-VL, Setting=Self-SD2026.04 | 20.6 | — | 1 | |
| LVSPECModel=LLaVA-OV, Setting=Std.-SD2026.04 | 19.44 | 7.34 | 2.94 | |
| FLY⊖Model=Qwen2.5-VL, Setting=Std.-SD2026.04 | 18.5 | 6.81 | 2.32 | |
| NAIVE SDModel=Qwen2.5-VL, Setting=Self-SD2026.04 | 18.21 | 4.43 | 0.88 | |
| SPECVLMModel=Qwen2.5-VL, Setting=Std.-SD2026.04 | 15.9 | 3.29 | 2 | |
| SPECVLMModel=LLaVA-OV, Setting=Std.-SD2026.04 | 15.75 | 3.37 | 2.38 | |
| FLY⊖Model=LLaVA-OV, Setting=Std.-SD2026.04 | 13.82 | 4.83 | 2.09 | |
| FLYModel=Qwen2.5-VL, Setting=Std.-SD2026.04 | 13.6 | 4.37 | 1.71 | |
| NAIVE SDModel=LLaVA-OV, Setting=Std.-SD2026.04 | 12.5 | 3.4 | 1.89 | |
| FLYModel=LLaVA-OV, Setting=Std.-SD2026.04 | 12.17 | 4.12 | 1.84 | |
| NAIVE SDModel=Qwen2.5-VL, Setting=Std.-SD2026.04 | 11.17 | 3.28 | 1.41 | |
| AutoregressiveModel=Qwen2.5-VL, Setting=Std.-SD2026.04 | 7.95 | — | 1 | |
| AutoregressiveModel=LLaVA-OV, Setting=Std.-SD2026.04 | 6.62 | — | 1 |