Model card
all-MiniLM-L6-v2.
Sentence-Transformersopen-source22M paramsMiniLM-L6 (BERT-like)
Lightweight sentence embedding model. Published by UKP/Microsoft.
§ 01 · Benchmarks
Every benchmark all-MiniLM-L6-v2 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | STS Benchmark | Natural Language Processing · Semantic Textual Similarity | spearman | 82.8% | #3 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where all-MiniLM-L6-v2 actually performs.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
1
result
1 of 1 rows marked verified.