# Multimodal Reranking on MMEB Video v2 Source: [Multimodal Reranking on MMEB Video v2]() Collection index: [llms.txt]() Data updated: 2026-06-11T08:35:41.536Z Evaluation of model performance on the Multimodal Reranking task using the MMEB Video v2 benchmark suite, reporting scores for Classification (CLS), Question Answering (QA), Retrieval (RET), Multimodal Reranking (MRET), and Overall average. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Multimodal Reranking | | Dataset (including any stated split) | MMEB Video v2 | | Metric | Overall Average Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Overall Average Score](): Higher is better; unit: PERCENT. - [CLS Accuracy](): Higher is better; unit: PERCENT. - [QA Accuracy](): Higher is better; unit: PERCENT. - [RET Accuracy](): Higher is better; unit: PERCENT. - [MRET Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall Average Score | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-VL-8B-reranker | 62.9 | Not recorded | 6a28f37890966ade919c19ba | | Qwen3-VL-8B-miniReranker | 62.5 | Not recorded | 6a28f37890966ade919c19ba | | Qwen3-VL-Reranker-8B | 61 | Not recorded | 6a28f37890966ade919c19ba | | Qwen3-VL-4B-miniReranker | 60.9 | Not recorded | 6a28f37890966ade919c19ba | | Qwen3-VL-4B-reranker | 60.1 | Not recorded | 6a28f37890966ade919c19ba | | Qwen3-VL-2B-reranker | 58.8 | Not recorded | 6a28f37890966ade919c19ba | | Qwen3-VL-2B-miniReranker | 55 | Not recorded | 6a28f37890966ade919c19ba | | Qwen3-VL-Reranker-2B | 53.2 | Not recorded | 6a28f37890966ade919c19ba | | Qwen3-VL-2B-Instruct | 44 | Not recorded | 6a28f37890966ade919c19ba | | GME (7B) | 38.6 | Not recorded | 6a28f37890966ade919c19ba | | VLM2Vec-Qwen2VL (7B) | 34 | Not recorded | 6a28f37890966ade919c19ba | | GME (2B) | 33.9 | Not recorded | 6a28f37890966ade919c19ba | | LamRA-Qwen2.5 (7B) | 33.7 | Not recorded | 6a28f37890966ade919c19ba | | VLM2Vec (2B) | 29 | Not recorded | 6a28f37890966ade919c19ba | | ColPali v1.3 (3B) | 28.2 | Not recorded | 6a28f37890966ade919c19ba | ### Qwen3-VL-8B-reranker Overall Average Score: 62.9. Result ID: 6a2a7275fbc373592c278fed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"8B","Fine-tuning Recipe":"our training recipe"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-miniReranker Overall Average Score: 62.5. Result ID: 6a2a7275fbc373592c278fee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"8B","Fine-tuning Recipe":"our training recipe","Reranker Type":"miniReranker"}. This record does not assert independent reproduction. ### Qwen3-VL-Reranker-8B Overall Average Score: 61. Result ID: 6a2a7275fbc373592c278fec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"8B"}. This record does not assert independent reproduction. ### Qwen3-VL-4B-miniReranker Overall Average Score: 60.9. Result ID: 6a2a7275fbc373592c278fe8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"4B","Fine-tuning Recipe":"our training recipe","Reranker Type":"miniReranker"}. This record does not assert independent reproduction. ### Qwen3-VL-4B-reranker Overall Average Score: 60.1. Result ID: 6a2a7275fbc373592c278fe7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"4B","Fine-tuning Recipe":"our training recipe"}. This record does not assert independent reproduction. ### Qwen3-VL-2B-reranker Overall Average Score: 58.8. Result ID: 6a2a7275fbc373592c278fe5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"2B","Fine-tuning Recipe":"our training recipe"}. This record does not assert independent reproduction. ### Qwen3-VL-2B-miniReranker Overall Average Score: 55. Result ID: 6a2a7275fbc373592c278fe6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"2B","Fine-tuning Recipe":"our training recipe","Reranker Type":"miniReranker"}. This record does not assert independent reproduction. ### Qwen3-VL-Reranker-2B Overall Average Score: 53.2. Result ID: 6a2a7275fbc373592c278fe3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"2B"}. This record does not assert independent reproduction. ### Qwen3-VL-2B-Instruct Overall Average Score: 44. Result ID: 6a2a7275fbc373592c278fe4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"2B"}. This record does not assert independent reproduction. ### GME (7B) Overall Average Score: 38.6. Result ID: 6a2a7275fbc373592c278fe9. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"7B"}. This record does not assert independent reproduction. ### VLM2Vec-Qwen2VL (7B) Overall Average Score: 34. Result ID: 6a2a7275fbc373592c278feb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"7B"}. This record does not assert independent reproduction. ### GME (2B) Overall Average Score: 33.9. Result ID: 6a2a7275fbc373592c278fe1. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"2B"}. This record does not assert independent reproduction. ### LamRA-Qwen2.5 (7B) Overall Average Score: 33.7. Result ID: 6a2a7275fbc373592c278fea. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"7B"}. This record does not assert independent reproduction. ### VLM2Vec (2B) Overall Average Score: 29. Result ID: 6a2a7275fbc373592c278fe2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"2B"}. This record does not assert independent reproduction. ### ColPali v1.3 (3B) Overall Average Score: 28.2. Result ID: 6a2a7275fbc373592c278fe0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"3B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.