Text-to-text retrieval on MECAT
0.2545Recall@1OEA-Qwen7B
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| OEA-Qwen7BModel Category=OEA Models, Contrastive Learning (+Cl)=true2026.04 | 0.2545 | 0.4741 | 0.5867 | |
| OEA-Qwen7BModel Category=OEA Models, Contrastive Learning (+Cl)=false2026.04 | 0.2543 | 0.4719 | 0.5818 | |
| OEA-Qwen3BModel Category=OEA Models, Contrastive Learning (+Cl)=true2026.04 | 0.2465 | 0.4623 | 0.5824 | |
| OEA-Nemo3BModel Category=OEA Models, Contrastive Learning (+Cl)=true2026.04 | 0.228 | 0.4465 | 0.5566 | |
| OEA-Qwen3BModel Category=OEA Models, Contrastive Learning (+Cl)=false2026.04 | 0.226 | 0.4538 | 0.566 | |
| OEA-Nemo3BModel Category=OEA Models, Contrastive Learning (+Cl)=false2026.04 | 0.2211 | 0.4334 | 0.5499 | |
| MGA-CLAPModel Category=CLAP Models2026.04 | 0.1956 | 0.4064 | 0.5214 | |
| LAION-CLAPModel Category=CLAP Models2026.04 | 0.1806 | 0.3935 | 0.5057 | |
| Robust-CLAPModel Category=CLAP Models2026.04 | 0.1806 | 0.3935 | 0.5057 | |
| M2D-CLAPModel Category=CLAP Models2026.04 | 0.1792 | 0.3874 | 0.4951 | |
| Nemotron-3BModel Category=Vanilla LALMs, Retrieval Training=false2026.04 | 0.0686 | 0.2077 | 0.2956 | |
| Qwen2.5-Omni-3BModel Category=Vanilla LALMs, Retrieval Training=false2026.04 | 0.0318 | 0.0975 | 0.1539 | |
| Qwen2.5-Omni-7BModel Category=Vanilla LALMs, Retrieval Training=false2026.04 | 0.0316 | 0.1046 | 0.1592 |