EdTech Tracker

← Coding lens

ndcg

technique judged 81% likely a named technique or architecture

First seen
2024-05-28
Independent sources
7
Articles
14
Last 4 weeks vs prior
0 vs 4

See how it has spread across media tiers

Mentions over time

Articles per week (by publish date) using the term, in any spelling.
0122024-W222026-W242026-W41
Table view
WeekArticlesSources
2024-W2211
2024-W2911
2024-W3311
2026-W1111
2026-W1211
2026-W1511
2026-W2411
2026-W2511
2026-W3211
2026-W3611
2026-W3911
2026-W4022
2026-W4111

In their words

""" metrics = { " precision@k " : [], " recall@k " : [], " mrr " : [], " ndcg " : []} for tc in test_cases : results = self .

Recall@k, precision@k, MRR, nDCG, hit rate Generation Is the answer correct and based on the context?

Quality is the percentage of the baseline’s nDCG@10 retained, a score for how well the top 10 results rank relevant documents.

The table reports exact-search nDCG@10, which measures how well relevant documents rank in the first 10 results.

In our production evaluations on the BEIR benchmark, adding any of these rerankers on top of dense retrieval lifts NDCG@10 by 8–14 points, a bigger jump than switching embedding models.

On BRIGHT Biology, one of the hardest reasoning-intensive retrieval benchmarks, ultrahigh effort Search Mode lifts nDCG@10 to 57.5 compared to 13.0 with Hybrid Search alone.

Voyage-3-large scores ~74.8 NDCG@10 on MTEB v2 English retrieval, roughly 6 points above OpenAI text-embedding-3-large at comparable cost.

On the WANDS e-commerce benchmark, a tuned hybrid setup reaches 0.7497 NDCG — a 7.4% lift over either BM25 (0.6983) or pure vector search (0.6953) alone (Turnbull, 2025).