# MTEB(cmn, v1) · Chinese

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

Chinese text embedding quality across retrieval, reranking, pair classification, clustering, classification, and semantic similarity.

Canonical URL: https://benchize.com/benchmarks/mteb%3AMTEB(cmn%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.

Chinese text embedding quality across retrieval, reranking, pair classification, clustering, classification, and semantic similarity.

Embeddings · Models tested: 2 · Score publishers: [MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/research/C_MTEB)

## Model results

| # | Model | Score |  |
| --- | --- | --- | --- |
| 1 | [Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) | 0.74source score |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.7385685967741935 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.7501917698412699 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 83 ### Reported statistics experiments Not reported rank 8 scoresByTask {"AFQMC":0.528344,"ATEC":0.539912,"BQ":0.763131,"CLSClusteringP2P":0.742709,"CLSClusteringS2S":0.706935,"CMedQAv1-reranking":0.86132,"CMedQAv2-reranking":0.863852,"CmedqaRetrieval":0.52522,"Cmnli":0.843295,"CovidRetrieval":0.87653,"DuRetrieval":0.90939,"EcomRetrieval":0.72979,"IFlyTek":0.547441,"JDReview":0.88743,"LCQMC":0.801298,"MMarcoReranking":0.271429,"MMarcoRetrieval":0.8664,"MedicalRetrieval":0.65467,"MultilingualSentiment":0.8236165,"Ocnli":0.841364,"OnlineShopping":0.907,"PAWSX":0.543655,"QBQTC":0.407749,"STSB":0.862705,"T2Reranking":0.682946,"T2Retrieval":0.88987,"TNews":0.56733,"ThuNewsClusteringP2P":0.887944,"ThuNewsClusteringS2S":0.865571,"VideoRetrieval":0.80468,"Waimai":0.8921} scoresByTaskType {"Classification":0.7708195833333334,"Clustering":0.80078975,"PairClassification":0.8423295,"Reranking":0.66988675,"Retrieval":0.78206875,"STS":0.6352562857142858} trainedOnTasks ["CMedQAv2-reranking","CmedqaRetrieval","DuRetrieval","MMarcoReranking","T2Retrieval"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/MTEB(cmn%2C%20v1)/scores) Source MTEB Original model label Qwen/Qwen3-Embedding-8B Observed 2026-10-21T16:40:30.174Z Evidence SHA-256 `f29b711d6747ee5848d9b127e7517197a0d38a3c72a3ee75c810bd13b1c75370` Source locator `/rows/7` |  |  |  |
| 2 | [Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) | 0.72source score |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.7228334516129032 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.7351981964285713 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 83 ### Reported statistics experiments Not reported rank 14 scoresByTask {"AFQMC":0.508106,"ATEC":0.532428,"BQ":0.743034,"CLSClusteringP2P":0.711781,"CLSClusteringS2S":0.682058,"CMedQAv1-reranking":0.844303,"CMedQAv2-reranking":0.850626,"CmedqaRetrieval":0.50647,"Cmnli":0.840048,"CovidRetrieval":0.87373,"DuRetrieval":0.90102,"EcomRetrieval":0.7112,"IFlyTek":0.542362,"JDReview":0.862852,"LCQMC":0.795148,"MMarcoReranking":0.274541,"MMarcoRetrieval":0.8536,"MedicalRetrieval":0.63945,"MultilingualSentiment":0.8136,"Ocnli":0.826746,"OnlineShopping":0.8725,"PAWSX":0.446707,"QBQTC":0.401118,"STSB":0.861662,"T2Reranking":0.672706,"T2Retrieval":0.87942,"TNews":0.56442,"ThuNewsClusteringP2P":0.878822,"ThuNewsClusteringS2S":0.842879,"VideoRetrieval":0.7973,"Waimai":0.8772} scoresByTaskType {"Classification":0.755489,"Clustering":0.778885,"PairClassification":0.8333969999999999,"Reranking":0.660544,"Retrieval":0.77027375,"STS":0.6126004285714286} trainedOnTasks ["CMedQAv2-reranking","CmedqaRetrieval","DuRetrieval","MMarcoReranking","T2Retrieval"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/MTEB(cmn%2C%20v1)/scores) Source MTEB Original model label Qwen/Qwen3-Embedding-4B Observed 2026-10-21T16:40:30.174Z Evidence SHA-256 `f29b711d6747ee5848d9b127e7517197a0d38a3c72a3ee75c810bd13b1c75370` Source locator `/rows/13` |  |  |  |
| 3 | [Multilingual-E5-Large](https://benchize.com/models/multilingual-e5-large.md) | 0.58source score |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.577819545754138 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5787555260855569 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 52 scoresByTask {"AFQMC":0.33012696210135656,"ATEC":0.3980494990888422,"BQ":0.464386067989206,"CLSClusteringP2P":0.391453,"CLSClusteringS2S":0.368188,"CMedQAv1-reranking":0.67647,"CMedQAv2-reranking":0.66757,"CmedqaRetrieval":0.28656,"Cmnli":0.698256,"CovidRetrieval":0.75614,"DuRetrieval":0.853,"EcomRetrieval":0.54675,"IFlyTek":0.4186225471335129,"JDReview":0.8054409005628518,"LCQMC":0.7594603959481365,"MMarcoReranking":0.29117792745295484,"MMarcoRetrieval":0.79202,"MedicalRetrieval":0.5144,"MultilingualSentiment":0.7089666666666666,"Ocnli":0.586356,"OnlineShopping":0.9045,"PAWSX":0.14633512665991377,"QBQTC":0.274698,"STSB":0.8108128746883166,"T2Reranking":0.6632099500865187,"T2Retrieval":0.76072,"TNews":0.48801000000000005,"ThuNewsClusteringP2P":0.559314,"ThuNewsClusteringS2S":0.545622,"VideoRetrieval":0.58279,"Waimai":0.8629999999999999} scoresByTaskType {"Classification":0.6980900190605052,"Clustering":0.46614425,"PairClassification":0.642306,"Reranking":0.5746069693848684,"Retrieval":0.6365474999999999,"STS":0.45483841806796743} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/MTEB(cmn%2C%20v1)/scores) Source MTEB Original model label intfloat/multilingual-e5-large Observed 2026-10-21T16:40:30.174Z Evidence SHA-256 `f29b711d6747ee5848d9b127e7517197a0d38a3c72a3ee75c810bd13b1c75370` Source locator `/rows/51` |  |  |  |

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