Qwen3-Embedding-0.6B: benchmark results

Provider: Alibaba. Access: Open.

Unified ELO 1483 ± 20, rank #804 of 1607 rated models, from 22 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
BTZSC - Emotion43.1Macro-F1 (%)85.3
SkMTEB - Clustering44.28Mean V-measure (%) over the five clustering datasets; higher85.2
BTZSC - Intent56.28Macro-F1 (%)73.5
BTZSC57.97Macro-F1 (%)61.8
BTZSC - Topic48.56Macro-F1 (%)55.9
SkillRet61.94NDCG@10 (0-100; first-stage dense retrieval of the gold skil52.9
SkMTEB - Classification62.84Mean accuracy (%) over the seven classification datasets; hi51.9
SABER-Math - Geometry62.9nDCG@10 (0-100) with exponential gain, printed 0 to 1 and sc50
SkMTEB70.53Mean score (%) across the 31 Slovak MTEB datasets over seven48.1
SABER-Math - Statement-Statement56.6Overall nDCG@10 (0-100) with exponential gain, printed 0 to 47.6
SkMTEB - Pair Classification64.46Mean score (%) over the three pair-classification datasets; 44.4
SkMTEB - STS83.14Mean score (%) over the two semantic-textual-similarity data44.4

Interactive version: theaggregate.ai/model?slug=qwen3-embedding-0-6b · How It Works · Data refreshed daily, snapshot 2026-09-29.