ModelCards
← All benchmarks

MTEB Multilingual, retrieval

We haven't written a description for this benchmark yet; see the card notes below for how each maker ran it.

Your workloadRAG over docs · 12K in · 600 out · 50K requests/mo · 30% cached
  1. 1Qwen3-Embedding-8B · Alibaba
    70.88 score
  2. 2jina-embeddings-v5-text-small · Jina AI
    64.88 score

“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.

How each maker reported it

  • Qwen3-Embedding-8B technical report Tables 2–3; model card

    Alibaba's own numbers. Competitor scores were taken from the MTEB leaderboard in early June 2025. CMTEB for the 8B is 73.84 in the model card and Table 8 vs 73.83 in Table 3.

  • jina-embeddings-v5-text-small tech report Tables 2–4

    Jina's own numbers. † in the report marks some competitor scores as (partly) self-evaluated, including all voyage-4-nano scores. Qwen3-Embedding-4B is the teacher model.

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.