beir 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 beir.
Ndcg@10 is the reported evaluation metric for beir. 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 | NV-Embed-v2 | verified | 62.65 | 2026 | Source ↗ | Looks wrong? |
| 02 | GTE-Qwen2-7B-instruct | verified | 60.25 | 2026 | Source ↗ | Looks wrong? |
| 03 | E5-Mistral-7B-instruct | verified | 56.9 | 2026 | Source ↗ | Looks wrong? |
| 04 | ColBERTv2 | verified | 49.4 | 2026 | Source ↗ | Looks wrong? |