Text-to-Video Retrieval on MSRVTT (T2V)
55.5T2V ScoreQwen3-VL-emb-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-VL-emb-8BModel Type=Embedding Model2026.04 | 55.5 | |
| Qwen3-VL-emb-8B + DS2MModel Type=Embedding Model, Fine-tuning Data=DS2M2026.04 | 51.5 | |
| Qwen3-VL-8B + Ego4D + DS2MModel Type=Instruct Model, Fine-tuning Data=Ego4D + DS2M2026.04 | 32.1 | |
| GME-7BModel Type=Comparison Model2026.04 | 31.8 | |
| Qwen3-VL-8BModel Type=Instruct Model2026.04 | 30.5 | |
| Qwen3-VL-8B + DS2MModel Type=Instruct Model, Fine-tuning Data=DS2M2026.04 | 30.5 | |
| Qwen3-VL-8B + Ego4DModel Type=Instruct Model, Fine-tuning Data=Ego4D2026.04 | 29 | |
| VLM2Vec-V2.0Model Type=Comparison Model2026.04 | 28.3 | |
| LamRA-Qwen2.5Model Type=Comparison Model2026.04 | 25 |