# BRIGHT · Reasoning Retrieval

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

Reasoning-intensive retrieval quality across real-world queries spanning diverse domains including economics, psychology, mathematics, and coding, drawn from naturally occurring and carefully curated human data.

Canonical URL: https://benchize.com/benchmarks/mteb%3ABRIGHT
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.

Reasoning-intensive retrieval quality across real-world queries spanning diverse domains including economics, psychology, mathematics, and coding, drawn from naturally occurring and carefully curated human data.

Embeddings · Models tested: 3 · Score publishers: [MTEB](https://brightbenchmark.github.io/)

## Model results

| # | Model | Score |  |
| --- | --- | --- | --- |
| 1 | [Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) | 0.18source score |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.17566 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.17566 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct -1 ### Reported statistics experiments Not reported rank 10 scoresByTask {"BrightRetrieval":0.17566} scoresByTaskType {"Retrieval":0.17566} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BRIGHT/scores) Source MTEB Original model label openai/text-embedding-3-large Observed 2026-10-21T16:40:29.916Z Evidence SHA-256 `b3be287be0beea7d05659deef5cb416b5d9a3c0dd9ddf9fb452418cd80365341` Source locator `/rows/9` |  |  |  |
| 2 | [All Mpnet Base V2](https://benchize.com/models/all-mpnet-base-v2.md) | 0.15source score |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.1459558333333333 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.1459558333333333 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 17 scoresByTask {"BrightRetrieval":0.1459558333333333} scoresByTaskType {"Retrieval":0.1459558333333333} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BRIGHT/scores) Source MTEB Original model label sentence-transformers/all-mpnet-base-v2 Observed 2026-10-21T16:40:29.916Z Evidence SHA-256 `b3be287be0beea7d05659deef5cb416b5d9a3c0dd9ddf9fb452418cd80365341` Source locator `/rows/16` |  |  |  |
| 3 | [BGE Large EN V1.5](https://benchize.com/models/bge-large-en-v1-5.md) | 0.14source score |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.13568916666666667 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.13568916666666667 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 18 scoresByTask {"BrightRetrieval":0.13568916666666667} scoresByTaskType {"Retrieval":0.13568916666666667} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BRIGHT/scores) Source MTEB Original model label BAAI/bge-large-en-v1.5 Observed 2026-10-21T16:40:29.916Z Evidence SHA-256 `b3be287be0beea7d05659deef5cb416b5d9a3c0dd9ddf9fb452418cd80365341` Source locator `/rows/17` |  |  |  |

---
Cite as: BRIGHT · Reasoning Retrieval — Benchize, https://benchize.com/benchmarks/mteb%3ABRIGHT (retrieved 2026-10-21)