# MTEB(tha, v1) · Thai

> Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/mteb%3AMTEB(tha%2C%20v1). When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/mteb%3AMTEB(tha%2C%20v1).

Thai text embedding quality across classification, clustering, pair classification, reranking, and retrieval. Tasks are native Thai or high-quality human translations; machine-translated and cross-lingual tasks are excluded.

Canonical URL: https://benchize.com/benchmarks/mteb%3AMTEB(tha%2C%20v1)
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.

Thai text embedding quality across classification, clustering, pair classification, reranking, and retrieval. Tasks are native Thai or high-quality human translations; machine-translated and cross-lingual tasks are excluded.

Embeddings · Models tested: 3 · Score publishers: MTEB

## Model results

| # | Model | Score |  |
| --- | --- | --- | --- |
| 1 | [Bge m3](https://benchize.com/models/bge-m3.md) | 0.64source score |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.6420824333333334 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.6176943821428571 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 80 ### Reported statistics experiments Not reported rank 12 scoresByTask {"BelebeleRetrieval":0.89969,"MIRACLReranking":0.68466,"MIRACLRetrievalHardNegatives.v2":0.82271,"MKQARetrieval":0.06032,"MTOPDomainClassification":0.8624099999999999,"MTOPIntentClassification":0.6527765,"MrTidyRetrieval":0.7977,"MultiLongDocReranking":0.58007,"MultiLongDocRetrieval":0.339785,"SIB200Classification":0.709886,"SIB200ClusteringS2S":0.362558,"WebFAQRetrieval":0.7537,"WisesightSentimentClassification.v2":0.365146,"XNLI":0.784705,"XQuADRetrieval":0.95512} scoresByTaskType {"Classification":0.6475546249999999,"Clustering":0.362558,"PairClassification":0.784705,"Reranking":0.6323650000000001,"Retrieval":0.6612892857142858} trainedOnTasks ["MIRACLReranking","MIRACLRetrievalHardNegatives.v2","MrTidyRetrieval"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/MTEB(tha%2C%20v1)/scores) Source MTEB Original model label BAAI/bge-m3 Observed 2026-10-21T16:40:36.633Z Evidence SHA-256 `d535310e5a7c0161f952cd0de3eb7d757500e970721ae4cda0f047c1ea5baa9a` Source locator `/rows/11` |  |  |  |
| 2 | [All Mpnet Base V2](https://benchize.com/models/all-mpnet-base-v2.md) | 0.12source score |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.12175432974686616 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.16775777495488414 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 33 scoresByTask {"BelebeleRetrieval":0.14360666666666666,"MIRACLReranking":0.03545,"MIRACLRetrievalHardNegatives.v2":0.00241,"MKQARetrieval":0.00584,"MTOPDomainClassification":0.1796725,"MTOPIntentClassification":0.0521495,"MrTidyRetrieval":0.00348,"MultiLongDocReranking":0.07746,"MultiLongDocRetrieval":0.03065,"SIB200Classification":0.19792733333333334,"SIB200ClusteringS2S":0.033114,"WebFAQRetrieval":0.20407,"WisesightSentimentClassification.v2":0.237214,"XNLI":0.5106709462029922,"XQuADRetrieval":0.1126} scoresByTaskType {"Classification":0.16674083333333334,"Clustering":0.033114,"PairClassification":0.5106709462029922,"Reranking":0.056455000000000005,"Retrieval":0.07180809523809525} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/MTEB(tha%2C%20v1)/scores) Source MTEB Original model label sentence-transformers/all-mpnet-base-v2 Observed 2026-10-21T16:40:36.633Z Evidence SHA-256 `d535310e5a7c0161f952cd0de3eb7d757500e970721ae4cda0f047c1ea5baa9a` Source locator `/rows/32` |  |  |  |
| 3 | [all-MiniLM-L6-v2](https://benchize.com/models/all-minilm-l6-v2.md) | 0.11source score |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.11387216435330062 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.16260202085734005 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 34 scoresByTask {"BelebeleRetrieval":0.12536333333333333,"MIRACLReranking":0.03623,"MIRACLRetrievalHardNegatives.v2":0.00462,"MKQARetrieval":0.00428,"MTOPDomainClassification":0.16207050817963709,"MTOPIntentClassification":0.048235564025396534,"MrTidyRetrieval":0.00274,"MultiLongDocReranking":0.05279,"MultiLongDocRetrieval":0.016710000000000003,"SIB200Classification":0.18843726628823546,"SIB200ClusteringS2S":0.035902618739313365,"WebFAQRetrieval":0.19424,"WisesightSentimentClassification.v2":0.221736,"XNLI":0.5132771747335934,"XQuADRetrieval":0.10145} scoresByTaskType {"Classification":0.15511983462331727,"Clustering":0.035902618739313365,"PairClassification":0.5132771747335934,"Reranking":0.044509999999999994,"Retrieval":0.06420047619047618} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/MTEB(tha%2C%20v1)/scores) Source MTEB Original model label sentence-transformers/all-MiniLM-L6-v2 Observed 2026-10-21T16:40:36.633Z Evidence SHA-256 `d535310e5a7c0161f952cd0de3eb7d757500e970721ae4cda0f047c1ea5baa9a` Source locator `/rows/33` |  |  |  |

---
Cite as: MTEB(tha, v1) · Thai — Benchize, https://benchize.com/benchmarks/mteb%3AMTEB(tha%2C%20v1) (retrieved 2026-10-21)