MAGMaR
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Article Generation | MAGMaR oracle (leaderboard snapshot) | Human Preference Score3.833 | 15 | |
| Grounded Multi-Video Question Answering | MAGMaR (test) | Reference Precision (Ref-P)82.2 | 11 | |
| Multi-video Grounding and Retrieval | MAGMaR Oracle Track 2026 (val) | Human Evaluation Score3.833 | 11 | |
| Video Retrieval | MAGMaR 2026 | nDCG@100.759 | 8 | |
| Report Generation | MAGMaR (test) | ROUGE-L18.39 | 5 | |
| Information Retrieval | MAGMaR (final) | Average Score75.9 | 5 | |
| Multimodal RAG Evaluation | MAGMaR Extrinsic Quality Judgment (EQJ) | Information Preservation (Retrieval)65 | 3 |
Showing 7 of 7 rows