EdTech Tracker

← Coding lens

mteb

tool judged 9% likely a named technique or architecture

First seen
2023-10-24
Independent sources
5
Articles
12
Last 4 weeks vs prior
0 vs 0

See how it has spread across media tiers

Mentions over time

Articles per week (by publish date) using the term, in any spelling.
0122023-W432026-W092026-W34
Table view
WeekArticlesSources
2023-W4311
2024-W2211
2024-W2311
2024-W3311
2024-W4111
2025-W0211
2026-W0911
2026-W1011
2026-W1111
2026-W2411
2026-W2511
2026-W3411

In their words

Profile a Hugging Face dataset Type in a Hugging Face dataset ID, such as stanfordnlp/imdb or mteb/tweet_sentiment_extraction, and a single input fans out to four operator nodes that analyze the dataset live using the Datasets Server API.

Best Embedding Models for RAG in 2026: OpenAI, Voyage, Cohere, and Jina Compared Voyage-3-large tops MTEB v2, Cohere Embed v4 handles 128K multimodal, OpenAI is the best default, and Jina wins multilingual.

Denser Retriever on MTEB Retrieval Benchmark# Denser Retriever, which combines dense vector search (Milvus) with sparse keyword retrieval (Elasticsearch) and an XGBoost ML reranker, was benchmarked across the MTEB retrieval datasets (Denser AI, 2024).

Top performer on MTEB benchmarks in its size class - e5-large-v2 — 1024 dimensions.

Gemini Embedding 2 improves over its predecessor and ranks in the top 5 on the MTEB Multilingual leaderboard for text.

| Model | Provider | Dimensions | Max Tokens | MTEB Score | Cost per 1M Tokens | Notes | |---|---|---|---|---|---|---| | text-embedding-3-large | OpenAI | 3,072 (configurable) | 8,191 | 64.6 | $0.13 | Best general-purpose commercial model, supports dimension reduction | | text-embedding-3-small | OpenAI | 1,536 (configurable) | 8,191 | 62.3 | $0.02 | 6.5x cheaper than large, good enough for many u

Denser also introduces several standout features: - Supports various search methods like keyword search, vector search, and advanced machine learning to refine results - Uses XGBoost to blend different search methods effectively - Sets a high standard for accuracy based on the MTEB retrieval benchmark - Has proven effectiveness in real-life applications, such as powering chatbots and creating smar

Our experiments on MTEB datasets show that the combination of keyword search, vector search and a reranker via an xgboost model can significantly improve the vector search.