# CoREB(v1) · CoREB

> Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/mteb%3ACoREB(v1). When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/mteb%3ACoREB(v1).

Code embedding and reranking quality across code-to-text, text-to-code, and code-to-code retrieval tasks, using counterfactually rewritten problems in five programming languages to limit training data contamination.

Canonical URL: https://benchize.com/benchmarks/mteb%3ACoREB(v1)
Last updated: Wed, 21 Oct 2026 18:52:20 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Code embedding and reranking quality across code-to-text, text-to-code, and code-to-code retrieval tasks, using counterfactually rewritten problems in five programming languages to limit training data contamination.

Embeddings · Models tested: 1 · Score publishers: [MTEB](https://arxiv.org/abs/2605.04615)

## Model results

| # | Model | Score |  |
| --- | --- | --- | --- |
| 1 | [Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) | 0.59source score |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5895250000000001 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5895250000000001 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 5 scoresByTask {"CorebC2CReranking":0.40392,"CorebC2CRetrieval":0.54934,"CorebC2TReranking":0.93515,"CorebC2TRetrieval":0.94252,"CorebT2CReranking":0.28394,"CorebT2CRetrieval":0.42228} scoresByTaskType {"Reranking":0.5410033333333334,"Retrieval":0.6380466666666668} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/CoREB(v1)/scores) Source MTEB Original model label Qwen/Qwen3-Embedding-8B Observed 2026-10-21T16:40:38.910Z Evidence SHA-256 `9d28b52b2c83341c15981918e7671117838603977e1190fc2258d3feb15c938d` Source locator `/rows/5` |  |  |  |
| 2 | [Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) | 0.56source score |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5645883333333334 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5645883333333334 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 15 scoresByTask {"CorebC2CReranking":0.38025,"CorebC2CRetrieval":0.48473,"CorebC2TReranking":0.91246,"CorebC2TRetrieval":0.91698,"CorebT2CReranking":0.27769,"CorebT2CRetrieval":0.41542} scoresByTaskType {"Reranking":0.5234666666666666,"Retrieval":0.6057100000000001} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/CoREB(v1)/scores) Source MTEB Original model label Qwen/Qwen3-Embedding-4B Observed 2026-10-21T16:40:38.910Z Evidence SHA-256 `9d28b52b2c83341c15981918e7671117838603977e1190fc2258d3feb15c938d` Source locator `/rows/14` |  |  |  |

---
Cite as: CoREB(v1) · CoREB — Benchize, https://benchize.com/benchmarks/mteb%3ACoREB(v1) (retrieved 2026-10-21)