mxbai rerank base v2

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released June 202533K context≈ 24,576 words

A focused specialist that does one thing: score how relevant a document is to a query. It doesn't generate text or answer questions — it quietly sits in retrieval pipelines and re-orders candidate results by relevance. Compact and open-weight, it trades breadth for precision in that narrow ranking task.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Coding

Moderate

Factual Knowledge

Moderate

Instruction Following

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

Pricing

FreeOpen weight model

Details

License: apache-2.0
Input: text
Output: score
Languages: AF, AM, Arabic, AS, AZ, BE, Bulgarian, Bengali, BR, BS, Catalan, Czech, CY, Danish, German, Greek, English, EO, Spanish, Estonian, Basque, Persian, FF, Finnish, French, FY, GA, GD, Galician, GN, Gujarati, HA, Hebrew, Hindi, Croatian, HT, Hungarian, HY, Indonesian, IG, IS, Italian, Japanese, JV, KA, KK, Khmer, Kannada, Korean, KU, KY, LA, LG, LI, LN, Lao, Lithuanian, Latvian, MG, MK, Malayalam, MN, Marathi, Malay, Burmese, NE, Dutch, Norwegian, OM, OR, Punjabi, Polish, PS, Portuguese, QU, RM, Romanian, Russian, SA, SC, SD, SI, Slovak, Slovenian, SO, SQ, Serbian, SS, SU, Swedish, Swahili, Tamil, Telugu, Thai, Filipino, TN, Turkish, UG, Ukrainian, Urdu, UZ, Vietnamese, WO, XH, YI, YO, Chinese, ZU

Resources

HuggingFace

mxbai rerank base v2

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released June 202533K context≈ 24,576 words

A focused specialist that does one thing: score how relevant a document is to a query. It doesn't generate text or answer questions — it quietly sits in retrieval pipelines and re-orders candidate results by relevance. Compact and open-weight, it trades breadth for precision in that narrow ranking task.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Coding

Moderate

Factual Knowledge

Moderate

Instruction Following

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

Pricing

FreeOpen weight model

Details

License: apache-2.0
Input: text
Output: score
Languages: AF, AM, Arabic, AS, AZ, BE, Bulgarian, Bengali, BR, BS, Catalan, Czech, CY, Danish, German, Greek, English, EO, Spanish, Estonian, Basque, Persian, FF, Finnish, French, FY, GA, GD, Galician, GN, Gujarati, HA, Hebrew, Hindi, Croatian, HT, Hungarian, HY, Indonesian, IG, IS, Italian, Japanese, JV, KA, KK, Khmer, Kannada, Korean, KU, KY, LA, LG, LI, LN, Lao, Lithuanian, Latvian, MG, MK, Malayalam, MN, Marathi, Malay, Burmese, NE, Dutch, Norwegian, OM, OR, Punjabi, Polish, PS, Portuguese, QU, RM, Romanian, Russian, SA, SC, SD, SI, Slovak, Slovenian, SO, SQ, Serbian, SS, SU, Swedish, Swahili, Tamil, Telugu, Thai, Filipino, TN, Turkish, UG, Ukrainian, Urdu, UZ, Vietnamese, WO, XH, YI, YO, Chinese, ZU

Resources

HuggingFace

Glossary

PrecisionThe level of numerical detail a model uses to represent its internal values; higher precision means more accurate calculations but requires more memory.RankingThe process of ordering search results by relevance, determining which documents best match a user's query.Ranking TaskA machine learning task where the goal is to order a set of items by relevance or similarity to a query, commonly used in search engines and recommendation systems.RetrievalThe process of finding and returning relevant documents or information from a database based on a query.

Capabilities

Use Case Fit

Capabilities

Use Case Fit

Similar Models

Glossary