Text-to-Video Retrieval on MSRVTT (R@1)
49.9Recall@1FluxViT-B
Evaluation Results
| Method | Links | |
|---|---|---|
| FluxViT-BToken count=2048, Dual Softmax Loss=true, Zero-shot=true2025.03 | 49.9 | |
| FluxViT-BToken count=2048, Dual Softmax Loss=false, Zero-shot=true2025.03 | 49.8 | |
| VAST-GZero-shot=true2025.03 | 49.3 | |
| FluxViT-BToken count=1024, Dual Softmax Loss=true, Zero-shot=true2025.03 | 49.1 | |
| InternVideo2-6Bparameters=6B, citation=[55]2026.02 | 48.5 | |
| FluxViT-BToken count=1024, Dual Softmax Loss=false, Zero-shot=true2025.03 | 48 | |
| LanguageBindcitation=[79]2026.02 | 47.9 | |
| FluxViT-BToken count=512, Dual Softmax Loss=true, Zero-shot=true2025.03 | 47.2 | |
| GVE-7Bparameters=7B, citation=[20]2026.02 | 46.4 | |
| FluxViT-SToken count=2048, Dual Softmax Loss=true, Zero-shot=true2025.03 | 45 | |
| InternVideo2-1Bparameters=1B, citation=[55]2026.02 | 44.9 | |
| LanguageBind-HZero-shot=true2025.03 | 44.8 | |
| FluxViT-SToken count=1024, Dual Softmax Loss=true, Zero-shot=true2025.03 | 44.5 | |
| FluxViT-SToken count=2048, Dual Softmax Loss=false, Zero-shot=true2025.03 | 44.4 | |
| VideoCLIP-XLcitation=[48]2026.02 | 44.3 | |
| Embed-RL-4Bparameters=4B2026.02 | 44 | |
| Unite-7Bparameters=7B, citation=[27]2026.02 | 43.9 | |
| Embed-RL-2Bparameters=2B2026.02 | 43.7 | |
| GME-7Bparameters=7B, citation=[73]2026.02 | 43.6 | |
| GVE-3Bparameters=3B, citation=[20]2026.02 | 43.1 | |
| LanguageBind-LZero-shot=true2025.03 | 42.8 | |
| FluxViT-BToken count=512, Dual Softmax Loss=false, Zero-shot=true2025.03 | 42.6 | |
| ViClip-LZero-shot=true2025.03 | 42.4 | |
| FluxViT-SToken count=1024, Dual Softmax Loss=false, Zero-shot=true2025.03 | 42.2 | |
| InternVideo2-LZero-shot=true2025.03 | 42.1 | |
| InternVideo-LZero-shot=true2025.03 | 40.7 | |
| UMT-LZero-shot=true2025.03 | 40.7 | |
| InternVideoZero-shot=true, #Pairs=646M, #F=82026.03 | 40.7 | |
| FluxViT-SToken count=512, Dual Softmax Loss=true, Zero-shot=true2025.03 | 40.5 | |
| InternVideo2-BToken count=2048, Zero-shot=true2025.03 | 40.3 | |
| VideoPrism-GZero-shot=true2025.03 | 39.7 | |
| GME-2Bparameters=2B, citation=[73]2026.02 | 39 | |
| ViCLIPcitation=[54]2026.02 | 38.6 | |
| FluxViT-SToken count=512, Dual Softmax Loss=false, Zero-shot=true2025.03 | 36.8 | |
| Unite-2Bparameters=2B, citation=[27]2026.02 | 36.7 | |
| InternVideo2-SToken count=2048, Zero-shot=true2025.03 | 35.6 | |
| UMT-BZero-shot=true2025.03 | 35.2 | |
| UniME-7Bparameters=7B, citation=[18]2026.02 | 35.1 | |
| OmniVL-BZero-shot=true2025.03 | 34.6 | |
| OmniVLZero-shot=true, #Pairs=17M, #F=82026.03 | 34.6 | |
| VideoCoCa-GZero-shot=true2025.03 | 34.3 | |
| Singularity-BZero-shot=true2025.03 | 34 | |
| BGE-VLcitation=[77]2026.02 | 33.7 | |
| CLIP4Clipcitation=[40]2026.02 | 33.3 | |
| VLM2Vec-V2version=V2, citation=[41]2026.02 | 33 | |
| VINDLU-LZero-shot=true2025.03 | 32 | |
| VINDLUZero-shot=true, #Pairs=25M, #F=42026.03 | 32 | |
| ClusterSTMZero-shot=true, #Pairs=5M, #F=42026.03 | 31.2 | |
| CLIP4Clip-BZero-shot=true2025.03 | 30.6 | |
| CLIP4ClipZero-shot=true, #Pairs=400M, #F=122026.03 | 30.6 | |
| STMZero-shot=true, #Pairs=5M, #F=42026.03 | 29.8 | |
| UMTZero-shot=true, #Pairs=5M, #F=42026.03 | 29.6 | |
| SingularityZero-shot=true, #Pairs=5M, #F=122026.03 | 28.4 | |
| B3-7Bparameters=7B, citation=[46]2026.02 | 28.2 | |
| VIOLET-BZero-shot=true2025.03 | 25.9 | |
| VIOLETZero-shot=true, #Pairs=138M, #F=52026.03 | 25.9 | |
| VIOLETv2Zero-shot=true, #Pairs=5M, #F=52026.03 | 21.9 | |
| Frozen-BZero-shot=true2025.03 | 18.7 | |
| FrozenZero-shot=true, #Pairs=5M, #F=42026.03 | 18.7 |