Skip to content
AI Atlas
ModelActive

Qwen3 Embedding Series

Qwen Teamfamily · Qwen3qwen.ai

Open in Graph
quality58

Updated 2 h ago · first seen 12 Sept 2026

model_01M29XQXS734P2WJRH63K7ZQBR

Overview

Identity

Identity block not returned by the API for this entity.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Status

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Official page
qwen.ai

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Repository
github.com

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Architecture

Architecture

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Mixture of experts

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Capabilities

Modalities

Modalities
embeddingscoretext
Input
text
Output
embeddingscore

Capabilities

  • Tool calling

    Unavailable

  • Structured output

    Unavailable

  • Reasoning

    Unavailable

  • Vision

    No

    Qwen — official blog · T2

  • Audio

    No

    Qwen — official blog · T2

  • Fine-tuning available

    Yes

    Qwen — official blog · T2

Context window

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Languages

Source:Qwen — official blogT2observed 10 h agomediumLLM-extracted

Lineage

Open in Graph →
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
ANCESTORS 1Qwen3Qwen3Qwen3 Embedding Seriesthis modelQwen3 Embedding Series — this model

Timeline1

Full timeline →

Change history

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.
1 claims · 1 propertiesShow all properties

Training data notestraining_data_notes1

Claim history for Training data notes
ValueValid from → toStatusSourceConfidenceExtractor
Multi-stage training paradigm: contrastive pre-training with weakly supervised data, supervised training with high-quality labeled data, and merging strategy for embedding models; supervised training with high-quality labeled data for reranking models. → currentcurrentQwen — official blogT2mediumllm

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

18

Source tiers

T218

Freshest observation

10 h ago

Conflicts

None

Source documents 1

Source documents
SourceDocumentTypeTierLast observedSnapshots
Qwen — official blogqwenlm.github.io/blog/qwen3-embedding newsT1· Official10 h ago1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (58/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →