Benchmark
RTEB
Evaluate how well embedding models find relevant documents on unseen retrieval tasks.
Published leaderboard
Explore scores and evaluation settings on the publisher’s leaderboard.
Open leaderboardCoverage
Retrieval Embedding Benchmark, introduced in beta with open and private text-retrieval datasets across application domains.
Methodology
Measure retrieval quality, including NDCG@10, on the stated dataset split. Compare open-data results with private evaluations run by MTEB maintainers.