Model Profile
Qwen3-Embedding-4B
Use this page to decide where this model is a strong fit. Rankings below are benchmark-backed by use case, with explicit confidence and contributor metrics.
Identity
ID: Qwen/Qwen3-Embedding-4B
Author: Qwen
Origin: huggingface_catalog
Arch: unknown
Benchmark Coverage
Scored use cases: 12
Avg confidence: 14.0%
Evidence points: 89
Raw rows: 16
Weighted rows: 8
Catalog Metadata
Parameters: unknown
Context window: 4096
Downloads: 628,416
Intelligence Profile
Scoring in progressDimension scores will appear once benchmark scoring is complete for IQ, EQ, Accuracy, Creativity, and Based dimensions.
Benchmark Signals
Click through to the benchmark source behind this model profile.
MTEB STS & Summarization Proxy Official
sts_score_pct
Normalized value 99.5% · confidence 100.0%
Strongest impact in Multilingual Customer Support
mteb_sts_summarization_official.sts_score_pct · Apr 1, 2026
MTEB Classification Official
classification_score_pct
Normalized value 83.3% · confidence 100.0%
Strongest impact in Ticket triage and routing
mteb_classification_official.classification_score_pct · Apr 1, 2026
MTEB Retrieval and Rerank (Official)
retrieval_score_pct
Normalized value 88.8% · confidence 100.0%
Strongest impact in Agent-assist reply suggestions
mteb_retrieval_rerank_official.retrieval_score_pct · Apr 1, 2026
BEIR-Style Retrieval (Official MTEB Slice)
beir_average_score_pct
Normalized value 75.4% · confidence 100.0%
Strongest impact in Agent-assist reply suggestions
beir_retrieval_official.beir_average_score_pct · Apr 1, 2026
MTEB Retrieval and Rerank (Official)
reranking_score_pct
Normalized value 88.1% · confidence 100.0%
Strongest impact in Agent-assist reply suggestions
mteb_retrieval_rerank_official.reranking_score_pct · Apr 1, 2026
MTEB STS & Summarization Proxy Official
summarization_proxy_score_pct
Normalized value 99.5% · confidence 100.0%
Strongest impact in Toxicity moderation routing
mteb_sts_summarization_official.summarization_proxy_score_pct · Apr 1, 2026
Some fit rows have limited benchmark evidence.
12 of 12 scored use cases have low confidence or thin contributor coverage.
Coverage Diagnostics
actively scoredUse-Case Scores
25
Total Measurements
16
Weighted Measurements
8
Weighted Sources
4
Raw Source Coverage
Weighted Source Coverage
Best Use Cases for This Model
| Use Case | Score |
|---|---|
| Agent-assist reply suggestions use_case.cx.agent_assist_replies | 13.2% |
| Support FAQ bot use_case.cx.support_faq_bot | 13.1% |
| Support dialogue agent use_case.cx.support_dialogue_agent | 13.0% |
| Multilingual Customer Support use_case.cx.multilingual_support | 13.0% |
| Ticket triage and routing use_case.cx.ticket_triage | 12.6% |
| Toxicity moderation routing use_case.cx.toxicity_moderation | 12.4% |
| Spam filtering and classification use_case.cx.spam_filtering | 12.4% |
| Safety and policy gating use_case.cx.safety_gating | 12.1% |
| Support bot (RAG grounded) use_case.cx.support_rag_bot | 11.8% |
| Customer feedback theme mining use_case.cx.feedback_theme_mining | 11.6% |
| HR policy Q&A use_case.hr.hr_policy_qna | 11.5% |
| Ticket thread summary use_case.cx.ticket_thread_summary | 11.2% |