Video-based Dialogue Evaluation on Video-ChatGPT
3.06CIFULL CACHE
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| FULL CACHEModel Architecture=Qwen2.5-VL-7B2026.04 | 3.06 | 3.15 | 3.52 | 2.24 | 2.69 | 2.93 | |
| HYBRIDKVModel Architecture=Qwen2.5-VL-7B2026.04 | 2.99 | 3.05 | 3.47 | 2.15 | 2.57 | 2.85 | |
| FULL CACHEModel Architecture=LLaVA-OV-7B2026.04 | 2.99 | 2.86 | 3.36 | 2 | 2.99 | 2.84 | |
| HYBRIDKVModel Architecture=LLaVA-OV-7B2026.04 | 2.96 | 2.88 | 3.35 | 1.89 | 2.89 | 2.79 | |
| MADAKVModel Architecture=Qwen2.5-VL-7B2026.04 | 2.94 | 3.03 | 3.41 | 2.02 | 2.56 | 2.79 | |
| LOOK-MModel Architecture=Qwen2.5-VL-7B2026.04 | 2.92 | 2.97 | 3.38 | 2.05 | 2.49 | 2.76 | |
| SNAPKVModel Architecture=Qwen2.5-VL-7B2026.04 | 2.9 | 2.96 | 3.4 | 1.95 | 2.53 | 2.75 | |
| SPARSEMMModel Architecture=Qwen2.5-VL-7B2026.04 | 2.9 | 2.95 | 3.37 | 1.99 | 2.52 | 2.75 | |
| LOOK-MModel Architecture=LLaVA-OV-7B2026.04 | 2.9 | 2.75 | 3.32 | 1.87 | 2.87 | 2.74 | |
| MADAKVModel Architecture=LLaVA-OV-7B2026.04 | 2.9 | 2.79 | 3.35 | 1.9 | 2.89 | 2.77 | |
| SNAPKVModel Architecture=LLaVA-OV-7B2026.04 | 2.88 | 2.78 | 3.31 | 1.83 | 2.8 | 2.72 | |
| TemporalVLMData=100K2024.12 | 2.88 | 2.91 | 3.45 | 2.5 | 3.16 | — | |
| SPARSEMMModel Architecture=LLaVA-OV-7B2026.04 | 2.87 | 2.73 | 3.27 | 1.91 | 2.84 | 2.72 | |
| LongVLMData=100K2024.12 | 2.76 | 2.86 | 3.34 | 2.39 | 3.11 | — | |
| LOOK-MModel Architecture=Qwen2.5-VL-3B2026.04 | 2.74 | 2.68 | 3.1 | 1.85 | 2.23 | 2.52 | |
| HYBRIDKVModel Architecture=Qwen2.5-VL-3B2026.04 | 2.7 | 2.72 | 3.11 | 1.84 | 2.43 | 2.56 | |
| SPARSEMMModel Architecture=Qwen2.5-VL-3B2026.04 | 2.69 | 2.66 | 3.11 | 1.82 | 2.25 | 2.51 | |
| BT-AdapterData=10M2024.12 | 2.68 | 2.69 | 3.27 | 2.34 | 2.46 | — | |
| SNAPKVModel Architecture=Qwen2.5-VL-3B2026.04 | 2.64 | 2.67 | 3.09 | 1.77 | 2.23 | 2.48 | |
| MADAKVModel Architecture=Qwen2.5-VL-3B2026.04 | 2.6 | 2.64 | 3.03 | 1.81 | 2.39 | 2.49 | |
| FULL CACHEModel Architecture=Qwen2.5-VL-3B2026.04 | 2.59 | 2.67 | 3.06 | 1.93 | 2.49 | 2.55 | |
| Video-ChatGPTData=100K2024.12 | 2.5 | 2.57 | 2.69 | 2.16 | 2.2 | — | |
| ValleyData=234K2024.12 | 2.43 | 2.13 | 2.86 | 2.04 | 2.45 | — | |
| Video-LLaMAData=10M2024.12 | 1.96 | 2.18 | 2.16 | 1.82 | 1.79 | — |