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

← Catalog

mixedbread-ai/mxbai-rerank-large-v2

Open comparison →

Primitive: /score · Score · Qwen2

The crispy rerank family from Mixedbread.

MultilingualLong context

Overview

Hardware: — drives latency, throughput & cost

Size1.5B params
Tasks /score
Licenseapache-2.0
Languagesaf, am, ar, as, az, be, bg, bn, br, bs, ca, cs, cy, da, de, el, en, eo, es, et, eu, fa, ff, fi, fr, fy, ga, gd, gl, gn, gu, ha, he, hi, hr, ht, hu, hy, id, ig, is, it, ja, jv, ka, kk, km, kn, ko, ku, ky, la, lg, li, ln, lo, lt, lv, mg, mk, ml, mn, mr, ms, my, ne, nl, no, ns, om, or, pa, pl, ps, pt, qu, rm, ro, ru, sa, sc, sd, si, sk, sl, so, sq, sr, ss, su, sv, sw, ta, te, th, tl, tn, tr, ug, uk, ur, uz, vi, wo, xh, yi, yo, zh, zu
Latency767 ms
Throughput1.9K tok/s
Cost$0.118 /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 length8,192

Benchmarks

AskUbuntuDupQuestions

technology reranking en

Duplicate question detection from AskUbuntu

Corpus: 6,743 Queries: 360
Quality
ndcg at 10 0.6914
map at 10 0.5401
mrr at 10 0.7788
Performance L4 b1 c16
Corpus 1.3K tok/s
Corpus p50 74.5ms
Query 1.2K tok/s
Query p50 74.5ms
Reference →

CMedQAv1Reranking

medical reranking zh

Chinese medical question answering reranking (v1)

Corpus: 100,000 Queries: 2,000
Quality
map at 10 0.8304
mrr at 10 0.8633
Reference →

CMedQAv2Reranking

medical reranking zh

Chinese medical question answering reranking (v2)

Corpus: 108,000 Queries: 4,000
Quality
map at 10 0.8282
mrr at 10 0.8628
Reference →

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500
Performance L4 b1 c16
Query 1.9K tok/s
Query p50 535.4ms
Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648
Performance L4 b1 c16
Query 1.3K tok/s
Query p50 1.4s
Reference →

LegalBenchConsumerContractsQA

legal retrieval en

Question answering on consumer contracts

Corpus: 153 Queries: 396
Performance L4 b1 c16
Query 7.5K tok/s
Query p50 767.2ms
Reference →

MMarcoReranking

general reranking zh

Multilingual MARCO passage reranking (Chinese)

Quality
ndcg at 10 0.3836
map at 10 0.3174
mrr at 10 0.3480
Performance L4 b1 c16
Corpus 11.0K tok/s
Corpus p50 118.3ms
Query 857 tok/s
Query p50 118.3ms
Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Performance L4 b1 c16
Query 2.3K tok/s
Query p50 1.7s
Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300
Performance L4 b1 c16
Query 2.2K tok/s
Query p50 1.7s
Reference →

T2Reranking

general reranking zh

Chinese passage ranking benchmark

Quality
map at 10 0.5458
mrr at 10 0.7742
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.