ZeroEntropy vs Voyage
Pick a competitor. Same eval set, same judges, no hand-picked splits. The numbers below are computed live from /evals/.
ZeroEntropy vs OpenAI
penAI's text-embedding-3-large is the default many production stacks reach for — and zembed-1 outperforms it by 5-7 points Recall@100 across most verticals. OpenAI ships no first-party reranker, so the full pipeline gap is wider than the embedding gap alone.
- Common compatibility — OpenAI embeddings are wired into more vector DBs, frameworks, and downstream tooling than anything else on this list, so the integration cost of staying put is effectively zero.
- General-purpose embeddings beyond retrieval — text-embedding-3-large is broadly suitable for classification and clustering, where zembed-1 was specifically tuned for retrieval and may underweight other downstream tasks.
- Recall@100 — 5-7 point gap across most verticals on the eval set.
- The full retrieval pipeline — OpenAI ships no first-party reranker, so embed-only vs zembed-1 + zerank-2 is a single-stage-vs-two-stage comparison.
- Per-query cost at production scale — zembed-1 is materially cheaper per million tokens at every tier.
No cherry-picking. No hand-tuned splits.
Heterogeneous coverage — legal, finance, medical, multilingual, instruction-following, long-context. Every model evaluated on the same set.
Gemini-3-Flash, GPT-5-nano, Grok-4-fast. Inter-judge agreement (κ) ≥ 0.7 across the suite — see /concepts/eval-set-quality/ for the discipline.
Per-query deltas, not averaged independent samples. 95% CI on every reported number; statistical significance never asserted on n < 30.
