Sentence Transformers: multi-qa-mpnet-base-dot-v1

The multi-qa-mpnet-base-dot-v1 embedding model transforms sentences and short paragraphs into a 768-dimensional dense vector space, generating high-quality semantic embeddings optimized for question-…

sentence-transformers/multi-qa-mpnet-base-dot-v1-20251117

The multi-qa-mpnet-base-dot-v1 embedding model transforms sentences and short paragraphs into a 768-dimensional dense vector space, generating high-quality semantic embeddings optimized for question-and-answer retrieval, semantic search, and similarity-scoring across diverse content.

Specifications & capabilities

Input
text
Output
embeddings
Context window · tokens
512
Published model ID
multi-qa-mpnet-base-dot-v1
Capabilities
embeddings

Evaluations

1–7 / 7

MTEB

76.225%

source id
mteb
leaderboard name
MTEB Pair Classification
dimension
embedding
metric
Average task score
rank
47
sample size
12
aggregation scope
splits
  • test
subsets
  • cs
  • de
  • es
  • fr
  • hi
  • ja
  • ko
  • ms
  • nl
  • pt
  • tr
  • zh
task_count
1
task_names
  • PubChemWikiPairClassification
sample_size
12
subset_count
12
subset_sample
  • cs
  • de
  • es
  • fr
  • hi
  • ja
  • ko
  • ms
  • nl
  • pt
  • tr
  • zh
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 3af7c6da5b3e1bea796ef6c97fe237538cbe6e7f
source model id
sentence-transformers/multi-qa-mpnet-base-dot-v1
Original result ↗

MTEB

78.57%

source id
mteb
leaderboard name
MTEB Classification
dimension
embedding
metric
Average task score
rank
99
sample size
17
aggregation scope
splits
  • test
subsets
  • default
task_count
17
task_names
  • SDSEyeProtectionClassification
  • SDSGlovesClassification
  • WikipediaBioMetChemClassification
  • WikipediaBiolumNeurochemClassification
  • WikipediaChemEngSpecialtiesClassification
  • WikipediaChemFieldsClassification
  • WikipediaChemistryTopicsClassification
  • WikipediaCompChemSpectroscopyClassification
  • WikipediaCryobiologySeparationClassification
  • WikipediaCrystallographyAnalyticalClassification
  • WikipediaGreenhouseEnantiopureClassification
  • WikipediaIsotopesFissionClassification
  • WikipediaLuminescenceClassification
  • WikipediaOrganicInorganicClassification
  • WikipediaSaltsSemiconductorsClassification
  • WikipediaSolidStateColloidalClassification
  • WikipediaTheoreticalAppliedClassification
sample_size
17
subset_count
1
subset_sample
  • default
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 3af7c6da5b3e1bea796ef6c97fe237538cbe6e7f
source model id
sentence-transformers/multi-qa-mpnet-base-dot-v1
Original result ↗

MTEB

66.833%

source id
mteb
leaderboard name
MTEB Overall
dimension
embedding
metric
Average task score
rank
158
sample size
43
aggregation scope
splits
  • dev
  • test
  • train
subsets
  • canon-desc
  • canon-title
  • cs
  • de
  • default
  • es
  • fr
  • hi
  • iso-desc
  • iso-title
  • ja
  • ko
  • ms
  • nl
  • pt
  • tr
  • zh
task_count
27
task_names
  • ChemHotpotQARetrieval
  • ChemNQRetrieval
  • PubChemAISentenceParaphrasePC
  • PubChemSMILESBitextMining
  • PubChemSMILESPC
  • PubChemSynonymPC
  • PubChemWikiPairClassification
  • PubChemWikiParagraphsPC
  • SDSEyeProtectionClassification
  • SDSGlovesClassification
  • WikipediaBioMetChemClassification
  • WikipediaBiolumNeurochemClassification
  • WikipediaChemEngSpecialtiesClassification
  • WikipediaChemFieldsClassification
  • WikipediaChemistryTopicsClassification
  • WikipediaChemistryTopicsClustering
  • WikipediaCompChemSpectroscopyClassification
  • WikipediaCryobiologySeparationClassification
  • WikipediaCrystallographyAnalyticalClassification
  • WikipediaGreenhouseEnantiopureClassification
  • WikipediaIsotopesFissionClassification
  • WikipediaLuminescenceClassification
  • WikipediaOrganicInorganicClassification
  • WikipediaSaltsSemiconductorsClassification
  • WikipediaSolidStateColloidalClassification
  • WikipediaSpecialtiesInChemistryClustering
  • WikipediaTheoreticalAppliedClassification
sample_size
43
subset_count
17
subset_sample
  • canon-desc
  • canon-title
  • cs
  • de
  • default
  • es
  • fr
  • hi
  • iso-desc
  • iso-title
  • ja
  • ko
  • ms
  • nl
  • pt
  • tr
  • zh
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 3af7c6da5b3e1bea796ef6c97fe237538cbe6e7f
source model id
sentence-transformers/multi-qa-mpnet-base-dot-v1
Original result ↗

MTEB

0.056%

source id
mteb
leaderboard name
MTEB Bitext Mining
dimension
embedding
metric
Average task score
rank
288
sample size
4
aggregation scope
splits
  • test
subsets
  • canon-desc
  • canon-title
  • iso-desc
  • iso-title
task_count
1
task_names
  • PubChemSMILESBitextMining
sample_size
4
subset_count
4
subset_sample
  • canon-desc
  • canon-title
  • iso-desc
  • iso-title
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 3af7c6da5b3e1bea796ef6c97fe237538cbe6e7f
source model id
sentence-transformers/multi-qa-mpnet-base-dot-v1
Original result ↗

MTEB

61.228%

source id
mteb
leaderboard name
MTEB Retrieval
dimension
embedding
metric
Average task score
rank
309
sample size
4
aggregation scope
splits
  • dev
  • test
  • train
subsets
  • default
task_count
2
task_names
  • ChemHotpotQARetrieval
  • ChemNQRetrieval
sample_size
4
subset_count
1
subset_sample
  • default
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 3af7c6da5b3e1bea796ef6c97fe237538cbe6e7f
source model id
sentence-transformers/multi-qa-mpnet-base-dot-v1
Original result ↗

MTEB

42.13%

source id
mteb
leaderboard name
MTEB Clustering
dimension
embedding
metric
Average task score
rank
350
sample size
2
aggregation scope
splits
  • test
subsets
  • default
task_count
2
task_names
  • WikipediaChemistryTopicsClustering
  • WikipediaSpecialtiesInChemistryClustering
sample_size
2
subset_count
1
subset_sample
  • default
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 3af7c6da5b3e1bea796ef6c97fe237538cbe6e7f
source model id
sentence-transformers/multi-qa-mpnet-base-dot-v1
Original result ↗

MTEB

46.454%

source id
mteb
leaderboard name
MTEB Other
dimension
embedding
metric
Average task score
rank
554
sample size
4
aggregation scope
splits
  • test
subsets
  • default
task_count
4
task_names
  • PubChemAISentenceParaphrasePC
  • PubChemSMILESPC
  • PubChemSynonymPC
  • PubChemWikiParagraphsPC
sample_size
4
subset_count
1
subset_sample
  • default
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 3af7c6da5b3e1bea796ef6c97fe237538cbe6e7f
source model id
sentence-transformers/multi-qa-mpnet-base-dot-v1
Original result ↗

Published prices

1–2 / 2

Provider specifications & access

1–2 / 2

sentence-transformers/multi-qa-mpnet-base-dot-v1 ↗

source model id
HuggingFace/sentence-transformers-multi-qa-mpnet-base-dot-v1@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
unknown
architecture
input_modalities
  • text
output_modalities
  • embeddings
capabilities

    Source specification observations

    1–2 / 2

    openRouter ↗

    field
    context_length
    value
    512
    normalized value
    512
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    460
    normalized value
    460
    scope
    source-model
    source id
    openRouter
    confidence
    1

    Original sources

    1–10 / 10

    Hugging Face · sentence-transformers/multi-qa-mpnet-base-dot-v1 ↗

    Google Cloud · Model page ↗

    Microsoft Foundry · Model page ↗

    OpenRouter · Model page ↗

    Microsoft Foundry · Model documentation ↗

    Google Cloud · Catalog ↗

    Hugging Face · Catalog ↗

    Hugging Face · Catalog ↗

    Microsoft Foundry · Catalog ↗

    OpenRouter · Catalog ↗

    Source links

    1–5 / 5

    Hugging Face model card

    1–1 / 1

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace