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

← Catalog

cross-encoder/ms-marco-MiniLM-L-12-v2

Open comparison →

Primitive: /score · Score · BERT

This model was trained on the MS Marco Passage Ranking task.

Overview

Hardware: — drives latency, throughput & cost

Size33M params
Tasks /score
Licenseapache-2.0
Languagesen
Latency40 ms
Throughput26.4K tok/s
Cost$0.0084 /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 length512

Benchmarks

AskUbuntuDupQuestions

technology reranking en

Duplicate question detection from AskUbuntu

Corpus: 6,743 Queries: 360
Quality
ndcg at 10 0.6145
map at 10 0.4558
mrr at 10 0.6921
Performance L4 b1 c16
Query 8.2K tok/s
Query p50 31.7ms
Reference →

CMedQAv1Reranking

medical reranking zh

Chinese medical question answering reranking (v1)

Corpus: 100,000 Queries: 2,000
Quality
map at 10 0.1016
mrr at 10 0.1528
Reference →

CMedQAv2Reranking

medical reranking zh

Chinese medical question answering reranking (v2)

Corpus: 108,000 Queries: 4,000
Quality
map at 10 0.1218
mrr at 10 0.1812
Reference →

CQADupstackPhysicsRetrieval

scientific retrieval en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 Queries: 1,039
Quality
map at 10 0.3733
mrr at 10 0.4358
ndcg at 10 0.4301
Reference →

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500
Quality
map at 10 0.2058
mrr at 10 0.2238
ndcg at 10 0.2711
Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648
Quality
map at 10 0.3235
mrr at 10 0.4831
ndcg at 10 0.4062
Reference →

LegalBenchConsumerContractsQA

legal retrieval en

Question answering on consumer contracts

Corpus: 153 Queries: 396
Quality
map at 10 0.6764
mrr at 10 0.6808
ndcg at 10 0.7326
Reference →

MMarcoReranking

general reranking zh

Multilingual MARCO passage reranking (Chinese)

Quality
map at 10 0.0426
mrr at 10 0.0446
Performance L4 b1 c16
Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Quality
map at 10 0.2375
mrr at 10 0.5362
ndcg at 10 0.3352
Reference →

SCIDOCS

scientific retrieval en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 Queries: 1,000
Quality
map at 10 0.1073
mrr at 10 0.3340
ndcg at 10 0.1849
Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300
Quality
map at 10 0.6619
mrr at 10 0.6797
ndcg at 10 0.7081
Reference →

StackOverflowQA

technology retrieval en

Programming question answering from Stack Overflow

Corpus: 19,931 Queries: 1,994
Quality
map at 10 0.3038
mrr at 10 0.3230
ndcg at 10 0.3640
Reference →

T2Reranking

general reranking zh

Chinese passage ranking benchmark

Quality
map at 10 0.5184
mrr at 10 0.7511
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 3.3K

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.