Home/Browse/beir

beir

Unknown

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.

Benchmark Stats

Models4
Papers4
Metrics1

SOTA History

Only 4 models on this benchmark

Help build the community leaderboard — submit your model results.

ndcg@10

Higher is better

RankModelSourceScoreYearPaper
1NV-Embed-v2

NV-Embed-v2 average nDCG@10 on BEIR (15 datasets). Rank #1 retrieval on MTEB leaderboard.

Community62.652024Source
2GTE-Qwen2-7B-instruct

GTE-Qwen2-7B average nDCG@10 on BEIR (MTEB retrieval sub-task). From HF model card.

Community60.252024Source
3E5-Mistral-7B-instruct

E5-Mistral-7B average nDCG@10 on BEIR 15 datasets, from paper Table 1.

Community56.92024Source
4ColBERTv2

ColBERTv2 average nDCG@10 on BEIR 18 datasets. From original BEIR / ColBERTv2 papers.

Community49.42022Source

Submit a Result

beir Leaderboard | CodeSOTA | CodeSOTA