Qwen3-Embedding-8B: benchmark results

Provider: Alibaba. Access: Open.

Unified ELO 1538 ± 20, rank #631 of 1607 rated models, from 22 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
BTZSC - Emotion50.69Macro-F1 (%)100
SkMTEB - Retrieval86.27Mean score (%) over the five retrieval datasets; higher is b96.3
BTZSC - Intent58.93Macro-F1 (%)88.2
BTZSC - Sentiment89.16Macro-F1 (%)88.2
SkMTEB74.53Mean score (%) across the 31 Slovak MTEB datasets over seven85.2
SkMTEB - Reranking87.04Mean score (%) over the three reranking datasets; higher is 85.2
SkMTEB - STS86.54Mean score (%) over the two semantic-textual-similarity data85.2
SkMTEB - Classification65.94Mean accuracy (%) over the seven classification datasets; hi81.5
BTZSC59.13Macro-F1 (%)73.5
SkMTEB - Pair Classification66.65Mean score (%) over the three pair-classification datasets; 70.4
SkillRet63.64NDCG@10 (0-100; first-stage dense retrieval of the gold skil64.7
SkMTEB - Bitext Mining94.43Mean F1 (%) over the six bitext-mining datasets; higher is b63

Interactive version: theaggregate.ai/model?slug=qwen3-embedding-8b · How It Works · Data refreshed daily, snapshot 2026-09-29.