# BEIR > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/mteb%3ABEIR. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/mteb%3ABEIR. Zero-shot retrieval quality across a heterogeneous set of IR tasks and domains, providing a common framework for comparing NLP-based retrieval models. Canonical URL: https://benchize.com/benchmarks/mteb%3ABEIR 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. Zero-shot retrieval quality across a heterogeneous set of IR tasks and domains, providing a common framework for comparing NLP-based retrieval models. Embeddings · Models tested: 14 · Score publishers: [MTEB](https://arxiv.org/abs/2104.08663) ## Model results | # | Model | Score | | | --- | --- | --- | --- | | 1 | [Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) | 0.63source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.6275818666666667 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.6275818666666667 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 73 ### Reported statistics experiments Not reported rank 2 scoresByTask {"ArguAna":0.76852,"CQADupstackRetrieval":0.529398,"ClimateFEVER":0.47355,"DBPedia":0.49683,"FEVER":0.91882,"FiQA2018":0.64567,"HotpotQA":0.76776,"MSMARCO":0.43603,"NFCorpus":0.41448,"NQ":0.65247,"QuoraRetrieval":0.88901,"SCIDOCS":0.32742,"SciFact":0.78457,"TRECCOVID":0.94991,"Touche2020":0.35929} scoresByTaskType {"Retrieval":0.6275818666666667} trainedOnTasks ["FEVER","HotpotQA","MSMARCO","NQ"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label Qwen/Qwen3-Embedding-8B Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/1` | | | | | 2 | [Qwen3 Embedding](https://benchize.com/models/qwen3-embedding.md) | 0.62source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.6157822 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.6157822 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 73 ### Reported statistics experiments Not reported rank 7 scoresByTask {"ArguAna":0.7564,"CQADupstackRetrieval":0.502843,"ClimateFEVER":0.47426,"DBPedia":0.48226,"FEVER":0.91597,"FiQA2018":0.62654,"HotpotQA":0.74722,"MSMARCO":0.42721,"NFCorpus":0.411,"NQ":0.63133,"QuoraRetrieval":0.88062,"SCIDOCS":0.31444,"SciFact":0.78333,"TRECCOVID":0.92924,"Touche2020":0.35407} scoresByTaskType {"Retrieval":0.6157822} trainedOnTasks ["FEVER","HotpotQA","MSMARCO","NQ"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label Qwen/Qwen3-Embedding-4B Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/6` | | | | | 3 | [Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) | 0.55source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5543162 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5543162 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct -1 ### Reported statistics experiments Not reported rank 36 scoresByTask {"ArguAna":0.57992,"CQADupstackRetrieval":0.475373,"ClimateFEVER":0.30275,"DBPedia":0.44755,"FEVER":0.87937,"FiQA2018":0.55002,"HotpotQA":0.71578,"MSMARCO":0.40245,"NFCorpus":0.42071,"NQ":0.61273,"QuoraRetrieval":0.89051,"SCIDOCS":0.23071,"SciFact":0.7777,"TRECCOVID":0.79562,"Touche2020":0.23355} scoresByTaskType {"Retrieval":0.5543162} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label openai/text-embedding-3-large Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/35` | | | | | 4 | [BGE Large EN V1.5](https://benchize.com/models/bge-large-en-v1-5.md) | 0.54source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5434306666666667 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5434306666666667 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 93 ### Reported statistics experiments Not reported rank 55 scoresByTask {"ArguAna":0.64516,"CQADupstackRetrieval":0.42229,"ClimateFEVER":0.36567,"DBPedia":0.44106,"FEVER":0.87182,"FiQA2018":0.45021,"HotpotQA":0.74101,"MSMARCO":0.42493,"NFCorpus":0.38061,"NQ":0.55029,"QuoraRetrieval":0.8906500000000002,"SCIDOCS":0.2263,"SciFact":0.74644,"TRECCOVID":0.74696,"Touche2020":0.24806} scoresByTaskType {"Retrieval":0.5434306666666667} trainedOnTasks ["NQ"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label BAAI/bge-large-en-v1.5 Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/54` | | | | | 5 | [BGE Base EN V1.5](https://benchize.com/models/bge-base-en-v1-5.md) | 0.53source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5322516666666667 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5322516666666667 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 93 ### Reported statistics experiments Not reported rank 74 scoresByTask {"ArguAna":0.63752,"CQADupstackRetrieval":0.415925,"ClimateFEVER":0.31167,"DBPedia":0.4077,"FEVER":0.86289,"FiQA2018":0.40646,"HotpotQA":0.7259699999999999,"MSMARCO":0.41351,"NFCorpus":0.37367,"NQ":0.54146,"QuoraRetrieval":0.889,"SCIDOCS":0.21725,"SciFact":0.74345,"TRECCOVID":0.78029,"Touche2020":0.25701} scoresByTaskType {"Retrieval":0.5322516666666667} trainedOnTasks ["NQ"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label BAAI/bge-base-en-v1.5 Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/73` | | | | | 6 | [GTE-Large](https://benchize.com/models/gte-large.md) | 0.52source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5221828666666667 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5221828666666667 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct -1 ### Reported statistics experiments Not reported rank 82 scoresByTask {"ArguAna":0.57158,"CQADupstackRetrieval":0.431763,"ClimateFEVER":0.2882,"DBPedia":0.42371,"FEVER":0.8453399999999999,"FiQA2018":0.44499,"HotpotQA":0.67156,"MSMARCO":0.40859,"NFCorpus":0.38173,"NQ":0.54777,"QuoraRetrieval":0.88319,"SCIDOCS":0.23440000000000003,"SciFact":0.74265,"TRECCOVID":0.7021999999999999,"Touche2020":0.25507} scoresByTaskType {"Retrieval":0.5221828666666667} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label thenlper/gte-large Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/81` | | | | | 7 | [Multilingual-E5-Large](https://benchize.com/models/multilingual-e5-large.md) | 0.51source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5145277333333333 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5145277333333333 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 73 ### Reported statistics experiments Not reported rank 105 scoresByTask {"ArguAna":0.54357,"CQADupstackRetrieval":0.396736,"ClimateFEVER":0.25732,"DBPedia":0.413,"FEVER":0.8279,"FiQA2018":0.43815,"HotpotQA":0.71224,"MSMARCO":0.43698,"NFCorpus":0.33983,"NQ":0.64031,"QuoraRetrieval":0.89263,"SCIDOCS":0.17447,"SciFact":0.70196,"TRECCOVID":0.7115,"Touche2020":0.23132} scoresByTaskType {"Retrieval":0.5145277333333333} trainedOnTasks ["FEVER","HotpotQA","MSMARCO","NQ"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label intfloat/multilingual-e5-large Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/105` | | | | | 8 | [GTE-Base](https://benchize.com/models/gte-base.md) | 0.51source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5113875333333333 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5113875333333333 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct -1 ### Reported statistics experiments Not reported rank 93 scoresByTask {"ArguAna":0.57122,"CQADupstackRetrieval":0.429053,"ClimateFEVER":0.28103,"DBPedia":0.41185000000000005,"FEVER":0.8151899999999999,"FiQA2018":0.40758000000000005,"HotpotQA":0.6575,"MSMARCO":0.40209000000000006,"NFCorpus":0.37897,"NQ":0.52835,"QuoraRetrieval":0.88151,"SCIDOCS":0.23132000000000003,"SciFact":0.76178,"TRECCOVID":0.68783,"Touche2020":0.22554} scoresByTaskType {"Retrieval":0.5113875333333333} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label thenlper/gte-base Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/92` | | | | | 9 | [Text Embedding 3 Small](https://benchize.com/models/text-embedding-3-small.md) | 0.51source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5108277999999999 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5108277999999999 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct -1 ### Reported statistics experiments Not reported rank 102 scoresByTask {"ArguAna":0.55486,"CQADupstackRetrieval":0.425847,"ClimateFEVER":0.26856,"DBPedia":0.3997,"FEVER":0.79415,"FiQA2018":0.44909,"HotpotQA":0.63634,"MSMARCO":0.37016,"NFCorpus":0.38329,"NQ":0.52856,"QuoraRetrieval":0.88835,"SCIDOCS":0.20797,"SciFact":0.73368,"TRECCOVID":0.77903,"Touche2020":0.24283} scoresByTaskType {"Retrieval":0.5108277999999999} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label openai/text-embedding-3-small Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/101` | | | | | 10 | [E5-Large-v2](https://benchize.com/models/e5-large-v2.md) | 0.51source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5055580666666667 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5055580666666667 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 86 ### Reported statistics experiments Not reported rank 114 scoresByTask {"ArguAna":0.46427,"CQADupstackRetrieval":0.376641,"ClimateFEVER":0.22210000000000002,"DBPedia":0.44015,"FEVER":0.82829,"FiQA2018":0.41144,"HotpotQA":0.7313199999999999,"MSMARCO":0.43456000000000006,"NFCorpus":0.37134,"NQ":0.63444,"QuoraRetrieval":0.86839,"SCIDOCS":0.20498,"SciFact":0.72242,"TRECCOVID":0.66636,"Touche2020":0.20667} scoresByTaskType {"Retrieval":0.5055580666666667} trainedOnTasks ["MSMARCO","NQ"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label intfloat/e5-large-v2 Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/113` | | | | | 11 | [E5-Base-v2](https://benchize.com/models/e5-base-v2.md) | 0.5source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5030050666666667 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5030050666666667 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 86 ### Reported statistics experiments Not reported rank 118 scoresByTask {"ArguAna":0.44568,"CQADupstackRetrieval":0.385436,"ClimateFEVER":0.2656,"DBPedia":0.42225999999999997,"FEVER":0.8498699999999999,"FiQA2018":0.39883,"HotpotQA":0.6915,"MSMARCO":0.41765,"NFCorpus":0.35389,"NQ":0.58221,"QuoraRetrieval":0.86555,"SCIDOCS":0.18681,"SciFact":0.7194400000000001,"TRECCOVID":0.69633,"Touche2020":0.26402} scoresByTaskType {"Retrieval":0.5030050666666667} trainedOnTasks ["MSMARCO","NQ"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label intfloat/e5-base-v2 Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/117` | | | | | 12 | [Text Embedding Ada 002](https://benchize.com/models/text-embedding-ada-002.md) | 0.49source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.4924667333333333 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.4924667333333333 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct -1 ### Reported statistics experiments Not reported rank 124 scoresByTask {"ArguAna":0.57437,"CQADupstackRetrieval":0.416921,"ClimateFEVER":0.21636,"DBPedia":0.39388,"FEVER":0.74989,"FiQA2018":0.44407,"HotpotQA":0.60896,"MSMARCO":0.40913,"NFCorpus":0.36972,"NQ":0.51581,"QuoraRetrieval":0.87602,"SCIDOCS":0.1836,"SciFact":0.72746,"TRECCOVID":0.68474,"Touche2020":0.21607} scoresByTaskType {"Retrieval":0.4924667333333333} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label openai/text-embedding-ada-002 Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/123` | | | | | 13 | [All Mpnet Base V2](https://benchize.com/models/all-mpnet-base-v2.md) | 0.44source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.4381301333333333 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.4381301333333333 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 86 ### Reported statistics experiments Not reported rank 142 scoresByTask {"ArguAna":0.46521,"CQADupstackRetrieval":0.449592,"ClimateFEVER":0.21971,"DBPedia":0.32088,"FEVER":0.50863,"FiQA2018":0.49963,"HotpotQA":0.39294,"MSMARCO":0.39747,"NFCorpus":0.33289,"NQ":0.5045,"QuoraRetrieval":0.87455,"SCIDOCS":0.23765,"SciFact":0.6557,"TRECCOVID":0.51326,"Touche2020":0.19934} scoresByTaskType {"Retrieval":0.4381301333333333} trainedOnTasks ["MSMARCO","NQ"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label sentence-transformers/all-mpnet-base-v2 Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/141` | | | | | 14 | [all-MiniLM-L12-v2](https://benchize.com/models/all-minilm-l12-v2.md) | 0.43source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.42690866666666666 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.42690866666666666 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 86 ### Reported statistics experiments Not reported rank 156 scoresByTask {"ArguAna":0.47128,"CQADupstackRetrieval":0.42533,"ClimateFEVER":0.21572,"DBPedia":0.33355,"FEVER":0.55905,"FiQA2018":0.37274,"HotpotQA":0.44589,"MSMARCO":0.39033,"NFCorpus":0.3225,"NQ":0.46469,"QuoraRetrieval":0.87758,"SCIDOCS":0.21818,"SciFact":0.62639,"TRECCOVID":0.50816,"Touche2020":0.17224} scoresByTaskType {"Retrieval":0.42690866666666666} trainedOnTasks ["MSMARCO","NQ"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label sentence-transformers/all-MiniLM-L12-v2 Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/155` | | | | | 15 | [all-MiniLM-L6-v2](https://benchize.com/models/all-minilm-l6-v2.md) | 0.42source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.41949986666666667 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.41949986666666667 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 86 ### Reported statistics experiments Not reported rank 162 scoresByTask {"ArguAna":0.50167,"CQADupstackRetrieval":0.413248,"ClimateFEVER":0.20272,"DBPedia":0.3233,"FEVER":0.51934,"FiQA2018":0.36867,"HotpotQA":0.46513,"MSMARCO":0.36542,"NFCorpus":0.31594,"NQ":0.43869,"QuoraRetrieval":0.87552,"SCIDOCS":0.21641,"SciFact":0.64508,"TRECCOVID":0.47232,"Touche2020":0.16904} scoresByTaskType {"Retrieval":0.41949986666666667} trainedOnTasks ["MSMARCO","NQ"] ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/BEIR/scores) Source MTEB Original model label sentence-transformers/all-MiniLM-L6-v2 Observed 2026-10-21T16:40:29.416Z Evidence SHA-256 `aa692eb1a79edbe38d3f54eb90a444bff3d6c0f7b0d66e7893c86efe737c8e26` Source locator `/rows/161` | | | | --- Cite as: BEIR — Benchize, https://benchize.com/benchmarks/mteb%3ABEIR (retrieved 2026-10-21)