ModelSpec is an analysis of alternatives for AI models: it decides which models fit a job from your requirements, sourced benchmarks and real cost, and shows its work.
QZhou-Embedding vs Qwen3 Embedding 8B for Retrieval embeddings, as of 2026-09-23
Find an embedding model that ranks relevant documents well for retrieval.
Worked example as of 2026-09-23, from the public data image.
What the evidence says
The evidence separates them: Qwen3 Embedding 8B leads for Retrieval embeddings, with a 26% chance of being the best model in the full lineup for this job, as of 2026-09-23.
QZhou-Embedding has a 17% chance of matching or beating Qwen3 Embedding 8B on this job's objective.
probability bands: a model joins the leader when P(its score >= the leader's) >= 0.25 under the score posteriors; a weighted capability with an 80% interval wider than 2.8 is not enough evidence
Decision status: answered. P(best) and score intervals retain the full ranked lineup for this job, including models beyond this pair and models with thin evidence. Models with unknown objective values remain unranked and are outside this probability. P(best) is not a head-to-head probability. Separation from this challenger need not mean a unique best model across that lineup.
Scores and score intervals use the objective's dimensionless normalised units. Cost per task is in USD for the selected offering and the applied spec's task size. When task size is omitted, the engine uses its documented default. Unavailable means the engine returned no value.
| Model | Score | Score interval | P(best), ranked job lineup | Cost per task, USD | Selected offering: provider / region / tier | Capability estimates and intervals |
|---|---|---|---|---|---|---|
| QZhou-Embedding | 0.0 | [-0.910881, 0.910881] | 5% | Unavailable | Unavailable / Unavailable / Unavailable |
|
| Qwen3 Embedding 8B | 0.933479 | [0.062415, 1.804542] | 26% | Unavailable | Unavailable / Unavailable / Unavailable |
|
Strongest retrieval evidence, cost no object.
Requirements
model.class = vectoriser: Retrieval embeddings require the model class that emits vectors.
Preferences
retrieval: Rank only by the retrieval capability estimate.
Applied template spec
spec_version- 1
where- model.class = vectoriser
optimizeweightsretrieval- 1.0
Evidence for QZhou-Embedding
| Benchmark | Version | Measurement | Unit | Published interval | Evidence date | Measurement conditions | Provenance |
|---|---|---|---|---|---|---|---|
| mteb_eng_v2 | MTEB(eng, v2), mean over tasks | 75.97 | percent | Unavailable | 2026-09-30 |
| Source |
| mteb_v2_retrieval | MTEB(eng, v2), Retrieval task type | 67.12 | percent | Unavailable | 2026-09-30 |
| Source |
Missing facts for QZhou-Embedding
feature.batch: not_disclosedfeature.effort_controls: not_disclosedfeature.streaming: not_disclosedfeature.structured_output: not_disclosedfeature.tool_calling: not_disclosedmodel.max_output_tokens: not_disclosedorigin.lab_jurisdiction: not_disclosedorigin.weights_hosting: not_disclosed
Evidence for Qwen3 Embedding 8B
| Benchmark | Version | Measurement | Unit | Published interval | Evidence date | Measurement conditions | Provenance |
|---|---|---|---|---|---|---|---|
| mteb_eng_v2 | MTEB(eng, v2), mean over tasks | 75.23 | percent | Unavailable | 2026-09-30 |
| Source |
| mteb_multilingual_v2 | MTEB(Multilingual, v2), mean over tasks | 70.58 | percent | Unavailable | 2026-09-30 |
| Source |
| mteb_v2_retrieval | MTEB(eng, v2), Retrieval task type | 69.44 | percent | Unavailable | 2026-09-30 |
| Source |
Missing facts for Qwen3 Embedding 8B
feature.batch: not_disclosedfeature.effort_controls: not_disclosedfeature.streaming: not_disclosedfeature.structured_output: not_disclosedfeature.tool_calling: not_disclosedlicence.commercial_use: not_disclosedlicence.fine_tuning: not_disclosedlicence.output_training: not_disclosedlicence.user_cap: not_disclosedmodel.context_window: not_disclosedmodel.input_modalities: not_disclosedmodel.languages: unknownmodel.max_output_tokens: not_disclosedmodel.output_modalities: not_disclosedmodel.release_date: not_disclosedorigin.base_lineage: not_disclosedorigin.lab_jurisdiction: not_disclosedorigin.weights_hosting: not_disclosed
What this template teaches
Model class is a Must, while measured retrieval quality is a Prefer.
Decision dec_d3eb2f69b7ef1ea013efa71f on public snapshot snap_05a963d2477ac2fb.
Read the full dated job answer.
The live board uses current data. This link applies the template to its full lineup.
Human lookup is free on Decide. CLI, API, and MCP access requires a key. Access and pricing.