All tasks / Models

jina-embeddings-v5 (omni-small)

Jina AI's multilingual embedding models: v5-text (677M, 239M) and v5-omni for text, image, audio and video.

  • Jina AI (Elastic)
  • Open weights
  • Released Apr 2026

Official page

Where it ranks

Facts

Vendor
Jina AI (Elastic)
Family
Jina Embeddings
Released
Apr 2026
Weights
Open: download and run it yourself
License
CC-BY-NC-4.0
Parameters
1.63B
GPU memory to run locally
~4 GB (Board lists ~3.1 GB memory use for v5-omni-small (1.63B); v5-text-small (0.6B) needs ~1.1 GB.)
Access
Free (open weights)
Last verified
19 Oct 2026

Price from jina.ai, 19 Oct 2026.

Benchmark results

BenchmarkResultEntry on the leaderboardAs ofSource
Agentset Embedding Model Leaderboard1,566Jina Embeddings v5 Text Small
ELO from GPT-5-judged pairwise comparisons; rank 4 of 18; win rate 54.7%; page says 'Last updated: February 15, 2026'.
15 Feb 2026agentset.ai
MTEB(eng, v2)71.8%jinaai/jina-embeddings-v5-omni-small
Mean (Task) over all 41 tasks; board rank 14 (Borda); zero-shot share not declared on the board (-1); read from the leaderboard's public API.
19 Oct 2026mteb-leaderboard-backend.hf.space
MTEB(Multilingual, v2)67%jinaai/jina-embeddings-v5-omni-small
Mean (Task) over all 131 tasks; board rank 14 (Borda); zero-shot share not declared on the board (-1); read from the leaderboard's public API.
19 Oct 2026mteb-leaderboard-backend.hf.space

Where you can use it

Earlier versions

  • jina-embeddings-v5-text · Feb 2026
  • jina-embeddings-v4 · —

Sources