--- title: jinaai/jina-colbert-v2 (Score) description: Trained by Jina AI.. XLM-RoBERTa, 559M parameters. canonical_url: https://superlinked.com/models/jinaai-jina-colbert-v2--score last_updated: 2026-05-24 --- # jinaai/jina-colbert-v2 (Score) Trained by Jina AI. Source: [jinaai/jina-colbert-v2 on HuggingFace](https://huggingface.co/jinaai/jina-colbert-v2) ## Overview | Field | Value | |-------|-------| | Architecture | XLM-RoBERTa | | Parameters | 559M | | Tasks | Encode, Score | | Outputs | Multi-Vec | | Dimensions | Multi-Vec: 128 | | Max sequence length | 8,192 tokens | | License | cc-by-nc-4.0 | | Inputs | text | | Languages | multilingual, af, am, ar, as, az, be, bg, bn, br, bs, ca, cs, cy, da, de, el, en, eo, es, et, eu, fa, fi, fr, fy, ga, gd, gl, gu, ha, he, hi, hr, hu, hy, id, is, it, ja, jv, ka, kk, km, kn, ko, ku, ky, la, lo, lt, lv, mg, mk, ml, mn, mr, ms, my, ne, nl, no, om, or, pa, pl, ps, pt, ro, ru, sa, sd, si, sk, sl, so, sq, sr, su, sv, sw, ta, te, th, tl, tr, ug, uk, ur, uz, vi, xh, yi, zh | ## Benchmarks ### AskUbuntuDupQuestions Domain: technology · Task: reranking · Language: en Duplicate question detection from AskUbuntu Corpus: 6,743 · Queries: 360 **Quality:** ndcg at 10: 0.6391 · map at 10: 0.4833 · mrr at 10: 0.7290 [Reference](https://github.com/taolei87/askubuntu) ### CMedQAv1-reranking Domain: general · Task: reranking · Language: en **Quality:** ndcg at 10: 0.5026 · map at 10: 0.4465 · mrr at 10: 0.5249 ### CMedQAv2-reranking Domain: general · Task: reranking · Language: en **Quality:** ndcg at 10: 0.5066 · map at 10: 0.4502 · mrr at 10: 0.5342 ### CQADupstackPhysicsRetrieval Domain: scientific · Task: retrieval · Language: en Duplicate question retrieval from StackExchange Physics Corpus: 38,314 · Queries: 1,039 **Performance (L4-SPOT b1 c16):** Corpus 3.3K tok/s · Corpus p50 325.6ms · Query 163 tok/s · Query p50 490.5ms **Performance (L4 b1 c16):** Corpus 22.9K tok/s · Corpus p50 83.9ms · Query 2.9K tok/s · Query p50 59.2ms [Reference](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/) ### CosQA Domain: technology · Task: retrieval · Language: en Code search with natural language queries Corpus: 6,267 · Queries: 500 **Performance (L4-SPOT b1 c16):** Corpus 798 tok/s · Corpus p50 555.8ms · Query 127 tok/s · Query p50 364.0ms **Performance (L4 b1 c16):** Corpus 13.4K tok/s · Corpus p50 65.7ms · Query 1.6K tok/s · Query p50 60.4ms [Reference](https://arxiv.org/abs/2105.13239) ### FiQA2018 Domain: finance · Task: retrieval · Language: en Financial opinion mining and question answering Corpus: 57,599 · Queries: 648 **Performance (L4-SPOT b1 c16):** Corpus 1.7K tok/s · Corpus p50 656.4ms · Query 218 tok/s · Query p50 412.6ms **Performance (L4 b1 c16):** Corpus 25.8K tok/s · Corpus p50 95.6ms · Query 3.0K tok/s · Query p50 60.7ms [Reference](https://sites.google.com/view/fiqa/) ### LegalBenchConsumerContractsQA Domain: legal · Task: retrieval · Language: en Question answering on consumer contracts Corpus: 153 · Queries: 396 **Performance (L4-SPOT b1 c16):** Corpus 5.8K tok/s · Corpus p50 568.2ms · Query 216 tok/s · Query p50 517.1ms **Performance (L4 b1 c16):** Corpus 27.5K tok/s · Corpus p50 274.0ms · Query 3.1K tok/s · Query p50 74.2ms [Reference](https://huggingface.co/datasets/nguha/legalbench) ### MMarcoReranking Domain: general · Task: reranking · Language: zh Multilingual MARCO passage reranking (Chinese) **Quality:** ndcg at 10: 0.4141 · map at 10: 0.3374 · mrr at 10: 0.3398 [Reference](https://arxiv.org/abs/2304.03679) ### NFCorpus Domain: medical · Task: retrieval · Language: en Biomedical literature search from NutritionFacts.org Corpus: 3,593 · Queries: 323 **Performance (L4-SPOT b1 c16):** Corpus 3.0K tok/s · Corpus p50 622.8ms · Query 77 tok/s · Query p50 440.1ms **Performance (L4 b1 c16):** Corpus 30.3K tok/s · Corpus p50 156.2ms · Query 1.2K tok/s · Query p50 63.6ms [Reference](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/) ### SCIDOCS Domain: scientific · Task: retrieval · Language: en Citation prediction, document classification, and recommendation for scientific papers Corpus: 25,656 · Queries: 1,000 **Performance (L4-SPOT b1 c16):** Corpus 2.8K tok/s · Corpus p50 521.5ms · Query 165 tok/s · Query p50 520.0ms **Performance (L4 b1 c16):** Corpus 26.7K tok/s · Corpus p50 108.8ms · Query 2.7K tok/s · Query p50 62.0ms [Reference](https://allenai.org/data/scidocs) ### SciFact Domain: scientific · Task: retrieval · Language: en Scientific claim verification using research literature Corpus: 5,183 · Queries: 300 **Performance (L4-SPOT b1 c16):** Corpus 4.6K tok/s · Corpus p50 397.7ms · Query 269 tok/s · Query p50 436.5ms **Performance (L4 b1 c16):** Corpus 29.3K tok/s · Corpus p50 145.2ms · Query 3.9K tok/s · Query p50 65.2ms [Reference](https://github.com/allenai/scifact) ### StackOverflowQA Domain: technology · Task: retrieval · Language: en Programming question answering from Stack Overflow Corpus: 19,931 · Queries: 1,994 **Performance (L4-SPOT b1 c16):** Corpus 3.4K tok/s · Corpus p50 554.5ms · Query 3.9K tok/s · Query p50 505.2ms **Performance (L4 b1 c16):** Corpus 19.2K tok/s · Corpus p50 162.2ms · Query 40.0K tok/s · Query p50 88.2ms [Reference](https://arxiv.org/abs/2407.02883) ### T2Reranking Domain: general · Task: reranking · Language: zh Chinese passage ranking benchmark **Quality:** ndcg at 10: 0.7321 · map at 10: 0.5607 · mrr at 10: 0.7809 [Reference](https://arxiv.org/abs/2304.03679)