dish-embed: Food Embedding Benchmark Results

Domain-specialized food embedding model vs general-purpose alternatives. All models evaluated at 384 dimensions on identical benchmark data.

dish-embed

Qwen3-Embedding-0.6B (#1 MTEB)

OpenAI text-embedding-3-large

BGE-M3

multilingual-e5-large

All models evaluated at 384 dimensions on identical food-domain benchmark data. Higher is better for all metrics. Qwen3-Embedding-0.6B ranks #1 on the MTEB Multilingual leaderboard (April 2026).

April 2026
embed.statode.com