MTEB GermanQuAD-Retrieval
26 models with a score. Leader: most-embed-de with 97.7.
| Benchmark profile | |
|---|---|
| Task | Retrieval (de) |
| Metric | nDCG@10 |
| Direction | ↑ higher is better |
| Limitation | Ein Wert gilt fuer die gemessene Modellrevision und die volle Vektorlaenge; gekuerzte Laengen sind nicht gemessen (R-MESS). |
| Source | huggingface.co |
| Licence | CC0 — MTEB-Ergebnisse (embeddings-benchmark/results) |
Ranking (26)
No entry matches the filter.
| Model | Rank | Score | Developer | EU processing: InputEU in | EU processing: OutputEU out | all providers: Inputall in | all providers: Outputall out | Open weights | GPU memory (4-bit, derived)GPU memory |
|---|---|---|---|---|---|---|---|---|---|
| most-embed-de | 1 | 97.7 | malteos | – | – | – | – | ✓ yes | from 5 GB |
| snowflake-arctic-embed-l-v2.0 | 2 | 95.5 | Snowflake | – | – | – | – | ✓ yes | from 5 GB |
| bekko-embedding-v1-a25m | 3 | 95.4 | hotchpotch | – | – | – | – | ✓ yes | from 5 GB |
| bekko-embedding-v1-a8m | 4 | 95.2 | hotchpotch | – | – | – | – | ✓ yes | from 5 GB |
| E5-Mistral-7B | 4 | 95.2 | Microsoft | €0.02 | – | €0.02 | – | ✓ yes | from 8 GB |
| multilingual-e5-large-instruct | 6 | 94.7 | Microsoft | €0.03 | €0.02 | €0.009 | – | ✓ yes | from 5 GB |
| snowflake-arctic-embed-m-v2.0 | 7 | 94.5 | Snowflake | – | – | €0.036 | – | ✓ yes | from 5 GB |
| cohere-embed-multilingual-v3.0 | 8 | 94.3 | Cohere | – | – | €0.09 | – | – no | – |
| intfloat/multilingual-e5-large | 9 | 93.2 | Microsoft | €0.0082 | – | €0.0082 | – | ✓ yes | from 5 GB |
| multilingual-e5-small | 10 | 91.37 | – | – | €0.0067 | – | ✓ yes | from 5 GB | |
| gte-multilingual-base | 11 | 90.6 | Alibaba Cloud | – | – | – | – | ✓ yes | from 5 GB |
| granite-embedding-278m-multilingual | 12 | 89.1 | IBM | – | – | – | – | ✓ yes | from 5 GB |
| Cohere Embed 3 Model - English | 13 | 85.21 | Cohere | – | – | €0.09 | – | – | – |
| e5-large-v2 | 14 | 84.71 | – | – | – | €0.009 | – | ✓ yes | from 5 GB |
| snowflake-arctic-embed-l | 15 | 82.1 | Snowflake | – | – | – | – | ✓ yes | from 5 GB |
| bge-large-en-v1.5 | 16 | 79.8 | BAAI | – | – | €0.009 | – | ✓ yes | from 5 GB |
| gte-large | 17 | 79.64 | – | – | – | €0.009 | – | ✓ yes | from 5 GB |
| e5-base-v2 | 18 | 79.25 | – | – | – | €0.0045 | – | ✓ yes | from 5 GB |
| mxbai-embed-large-v1 | 19 | 78.4 | Mixedbread | – | – | – | – | ✓ yes | from 5 GB |
| bge-base-en-v1.5 | 20 | 76.2 | BAAI | – | – | €0.0045 | – | ✓ yes | from 5 GB |
| gte-base | 21 | 75.9 | – | – | – | €0.0045 | – | ✓ yes | from 5 GB |
| nomic-embed-text-v1.5 | 21 | 75.9 | Nomic AI | – | – | – | – | ✓ yes | from 5 GB |
| all-mpnet-base-v2 | 23 | 71.01 | – | – | – | €0.0045 | – | ✓ yes | from 5 GB |
| SNOWFLAKE ARCTIC-EMBED-M-V1.5 | 24 | 70.71 | Snowflake | – | – | €0.022 | – | ✓ yes | from 5 GB |
| All MiniLM L12 v2 | 25 | 66.9 | – | – | – | €0.0045 | – | ✓ yes | from 5 GB |
| all-MiniLM-L6-v2 | 26 | 63.7 | – | – | – | €0.0045 | – | ✓ yes | from 5 GB |
Equal scores share a rank. When filtering, the rank stays the position in the whole list. GPU memory “from …” is a lower bound (parameters × 0.55 GB + 4 GB). Prices: € per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 7 Nov 2026.
Scores: MTEB GermanQuAD-Retrieval, CC0 — MTEB-Ergebnisse (embeddings-benchmark/results). Taken unchanged from the source.