Why did we open-source our inference engine? Read the post

← Catalog

jinaai/jina-reranker-v2-base-multilingual

Open comparison →

Primitive: /score · Score · XLM-RoBERTa

Trained by Jina AI.

Multilingual

Overview

Hardware: — drives latency, throughput & cost

Size278M params
Tasks /score
Licensecc-by-nc-4.0
Languagesmultilingual
Latency38 ms
Throughput29.0K tok/s
Cost$0.0077 /1M tok

Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.

Scoring

Inputstext
Max sequence length1,024

Benchmarks

AskUbuntuDupQuestions

technology reranking en

Duplicate question detection from AskUbuntu

Corpus: 6,743 Queries: 360
Quality
ndcg at 10 0.6546
map at 10 0.5008
mrr at 10 0.7429
Performance L4 b1 c16
Query 8.3K tok/s
Query p50 32.0ms
Reference →

CMedQAv1Reranking

medical reranking zh

Chinese medical question answering reranking (v1)

Corpus: 100,000 Queries: 2,000
Quality
map at 10 0.2034
mrr at 10 0.2747
Reference →

CMedQAv2Reranking

medical reranking zh

Chinese medical question answering reranking (v2)

Corpus: 108,000 Queries: 4,000
Quality
map at 10 0.2063
mrr at 10 0.2837
Reference →

MMarcoReranking

general reranking zh

Multilingual MARCO passage reranking (Chinese)

Quality
map at 10 0.3433
mrr at 10 0.3622
Performance L4 b1 c16
Reference →

Open source inference for agents

Open-source inference for the models behind your agents. Run it yourself, or let us run it for you.

Github 2.1K

Contact us

Tell us about your use case and we'll get back to you shortly.

Apply for an inference grant

Free capacity on our hosted cluster for selected projects. Tell us what you run and we reply by email.