Multimodal Reranking on MMEB Video v2
62.9Overall Average ScoreQwen3-VL-8B-reranker
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Qwen3-VL-8B-rerankerModel Scale=8B, Fine-tuning Recipe=our training recipe2026.06 | 62.9 | 65.6 | 67.1 | 61.7 | 53.3 | |
| Qwen3-VL-8B-miniRerankerModel Scale=8B, Fine-tuning Recipe=our training recipe, Reranker Type=miniReranker2026.06 | 62.5 | 67.2 | 67.3 | 60.9 | 48 | |
| Qwen3-VL-Reranker-8BModel Scale=8B2026.06 | 61 | — | — | — | — | |
| Qwen3-VL-4B-miniRerankerModel Scale=4B, Fine-tuning Recipe=our training recipe, Reranker Type=miniReranker2026.06 | 60.9 | 64.5 | 64 | 59.2 | 52.7 | |
| Qwen3-VL-4B-rerankerModel Scale=4B, Fine-tuning Recipe=our training recipe2026.06 | 60.1 | 63.2 | 63.6 | 60.6 | 48.3 | |
| Qwen3-VL-2B-rerankerModel Scale=2B, Fine-tuning Recipe=our training recipe2026.06 | 58.8 | 63.8 | 60.3 | 57.8 | 49.5 | |
| Qwen3-VL-2B-miniRerankerModel Scale=2B, Fine-tuning Recipe=our training recipe, Reranker Type=miniReranker2026.06 | 55 | 62.5 | 50.8 | 57.6 | 45.2 | |
| Qwen3-VL-Reranker-2BModel Scale=2B2026.06 | 53.2 | — | — | — | — | |
| Qwen3-VL-2B-InstructModel Scale=2B2026.06 | 44 | 60.2 | 55.4 | 20.9 | 36.7 | |
| GME (7B)Model Scale=7B2026.06 | 38.6 | 37.4 | 50.4 | 28.4 | 38.2 | |
| VLM2Vec-Qwen2VL (7B)Model Scale=7B2026.06 | 34 | 39.1 | 30 | 29 | 40.6 | |
| GME (2B)Model Scale=2B2026.06 | 33.9 | 34.9 | 42 | 25.6 | 32.4 | |
| LamRA-Qwen2.5 (7B)Model Scale=7B2026.06 | 33.7 | 32.9 | 42.6 | 23.2 | 37.6 | |
| VLM2Vec (2B)Model Scale=2B2026.06 | 29 | 33.4 | 30.5 | 20.6 | 33 | |
| ColPali v1.3 (3B)Model Scale=3B2026.06 | 28.2 | 26.7 | 37.8 | 21.6 | 25.5 |