ms-marco is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for ms-marco.
Mrr@10 is the reported evaluation metric for ms-marco. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Higher is better
Muted rows were not state of the art when published — an earlier or same-year result already scored better.
| Rank | Model | Trust | Score | Year | Links | Fix |
|---|---|---|---|---|---|---|
| 01 | RankLLaMA-7B | verified | 41.8 | 2026 | Source ↗ | Looks wrong? |
| 02 | jina-reranker-v2-base-multilingual | verified | 41.2 | 2026 | Source ↗ | Looks wrong? |
| 03 | ColBERTv2 | verified | 39.7 | 2026 | Source ↗ | Looks wrong? |
| 04 | MonoT5-3B | verified | 39 | 2026 | Source ↗ | Looks wrong? |