# LongEmbed · Long-context Retrieval > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/mteb%3ALongEmbed. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/mteb%3ALongEmbed. Long-context retrieval quality across synthetic and real-world tasks featuring documents of varying length with dispersed target information. Canonical URL: https://benchize.com/benchmarks/mteb%3ALongEmbed 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. Long-context retrieval quality across synthetic and real-world tasks featuring documents of varying length with dispersed target information. Embeddings · Models tested: 13 · Score publishers: [MTEB](https://arxiv.org/abs/2404.12096v2) ## Model results | # | Model | Score | | | --- | --- | --- | --- | | 1 | [Bge m3](https://benchize.com/models/bge-m3.md) | 0.59source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.59458 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.59458 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 37 scoresByTask {"LEMBNarrativeQARetrieval":0.48787,"LEMBNeedleRetrieval":0.395,"LEMBPasskeyRetrieval":0.59,"LEMBQMSumRetrieval":0.36114,"LEMBSummScreenFDRetrieval":0.93891,"LEMBWikimQARetrieval":0.79456} scoresByTaskType {"Retrieval":0.59458} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label BAAI/bge-m3 Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/36` | | | | | 2 | [Text Embedding 3 Small](https://benchize.com/models/text-embedding-3-small.md) | 0.54source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5355016666666667 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5355016666666667 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct -1 ### Reported statistics experiments Not reported rank 44 scoresByTask {"LEMBNarrativeQARetrieval":0.47232,"LEMBNeedleRetrieval":0.3675,"LEMBPasskeyRetrieval":0.385,"LEMBQMSumRetrieval":0.38145,"LEMBSummScreenFDRetrieval":0.92121,"LEMBWikimQARetrieval":0.68553} scoresByTaskType {"Retrieval":0.5355016666666667} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label openai/text-embedding-3-small Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/43` | | | | | 3 | [Text Embedding 3 Large](https://benchize.com/models/text-embedding-3-large.md) | 0.52source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.5242316666666667 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.5242316666666667 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct -1 ### Reported statistics experiments Not reported rank 50 scoresByTask {"LEMBNarrativeQARetrieval":0.44088,"LEMBNeedleRetrieval":0.2925,"LEMBPasskeyRetrieval":0.6975,"LEMBQMSumRetrieval":0.32493,"LEMBSummScreenFDRetrieval":0.84799,"LEMBWikimQARetrieval":0.54159} scoresByTaskType {"Retrieval":0.5242316666666667} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label openai/text-embedding-3-large Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/49` | | | | | 4 | [E5-Large-v2](https://benchize.com/models/e5-large-v2.md) | 0.43source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.42876 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.42876 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 56 scoresByTask {"LEMBNarrativeQARetrieval":0.26376,"LEMBNeedleRetrieval":0.315,"LEMBPasskeyRetrieval":0.385,"LEMBQMSumRetrieval":0.25083,"LEMBSummScreenFDRetrieval":0.77364,"LEMBWikimQARetrieval":0.58433} scoresByTaskType {"Retrieval":0.42876} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label intfloat/e5-large-v2 Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/55` | | | | | 5 | [E5-Base-v2](https://benchize.com/models/e5-base-v2.md) | 0.41source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.41051666666666664 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.41051666666666664 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 73 scoresByTask {"LEMBNarrativeQARetrieval":0.25317,"LEMBNeedleRetrieval":0.28500000000000003,"LEMBPasskeyRetrieval":0.38,"LEMBQMSumRetrieval":0.23859,"LEMBSummScreenFDRetrieval":0.74661,"LEMBWikimQARetrieval":0.55973} scoresByTaskType {"Retrieval":0.41051666666666664} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label intfloat/e5-base-v2 Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/72` | | | | | 6 | [Multilingual-E5-Large](https://benchize.com/models/multilingual-e5-large.md) | 0.4source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.40441666666666665 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.40441666666666665 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 72 scoresByTask {"LEMBNarrativeQARetrieval":0.24221,"LEMBNeedleRetrieval":0.28,"LEMBPasskeyRetrieval":0.3825,"LEMBQMSumRetrieval":0.24262,"LEMBSummScreenFDRetrieval":0.71117,"LEMBWikimQARetrieval":0.568} scoresByTaskType {"Retrieval":0.40441666666666665} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label intfloat/multilingual-e5-large Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/71` | | | | | 7 | [BGE Large EN V1.5](https://benchize.com/models/bge-large-en-v1-5.md) | 0.4source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.40059500000000003 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.40059500000000003 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 80 scoresByTask {"LEMBNarrativeQARetrieval":0.2792,"LEMBNeedleRetrieval":0.2725,"LEMBPasskeyRetrieval":0.3675,"LEMBQMSumRetrieval":0.23287,"LEMBSummScreenFDRetrieval":0.68726,"LEMBWikimQARetrieval":0.56424} scoresByTaskType {"Retrieval":0.40059500000000003} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label BAAI/bge-large-en-v1.5 Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/79` | | | | | 8 | [GTE-Large](https://benchize.com/models/gte-large.md) | 0.39source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.386725 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.386725 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct -1 ### Reported statistics experiments Not reported rank 89 scoresByTask {"LEMBNarrativeQARetrieval":0.30555,"LEMBNeedleRetrieval":0.27,"LEMBPasskeyRetrieval":0.38,"LEMBQMSumRetrieval":0.22407,"LEMBSummScreenFDRetrieval":0.64899,"LEMBWikimQARetrieval":0.49174} scoresByTaskType {"Retrieval":0.386725} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label thenlper/gte-large Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/88` | | | | | 9 | [GTE-Base](https://benchize.com/models/gte-base.md) | 0.35source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.34833166666666665 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.34833166666666665 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct -1 ### Reported statistics experiments Not reported rank 111 scoresByTask {"LEMBNarrativeQARetrieval":0.28602,"LEMBNeedleRetrieval":0.245,"LEMBPasskeyRetrieval":0.31,"LEMBQMSumRetrieval":0.2178,"LEMBSummScreenFDRetrieval":0.55831,"LEMBWikimQARetrieval":0.47286} scoresByTaskType {"Retrieval":0.34833166666666665} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label thenlper/gte-base Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/110` | | | | | 10 | [BGE Base EN V1.5](https://benchize.com/models/bge-base-en-v1-5.md) | 0.34source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.3388683333333334 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.3388683333333334 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 112 scoresByTask {"LEMBNarrativeQARetrieval":0.25632,"LEMBNeedleRetrieval":0.2525,"LEMBPasskeyRetrieval":0.18000000000000002,"LEMBQMSumRetrieval":0.22434,"LEMBSummScreenFDRetrieval":0.6034,"LEMBWikimQARetrieval":0.51665} scoresByTaskType {"Retrieval":0.3388683333333334} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label BAAI/bge-base-en-v1.5 Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/111` | | | | | 11 | [All Mpnet Base V2](https://benchize.com/models/all-mpnet-base-v2.md) | 0.31source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.31121333333333334 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.31121333333333334 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 129 scoresByTask {"LEMBNarrativeQARetrieval":0.19337,"LEMBNeedleRetrieval":0.16,"LEMBPasskeyRetrieval":0.245,"LEMBQMSumRetrieval":0.21538,"LEMBSummScreenFDRetrieval":0.60432,"LEMBWikimQARetrieval":0.44921} scoresByTaskType {"Retrieval":0.31121333333333334} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label sentence-transformers/all-mpnet-base-v2 Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/128` | | | | | 12 | [all-MiniLM-L6-v2](https://benchize.com/models/all-minilm-l6-v2.md) | 0.3source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.29811499999999996 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.29811499999999996 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 138 scoresByTask {"LEMBNarrativeQARetrieval":0.18268,"LEMBNeedleRetrieval":0.19999999999999998,"LEMBPasskeyRetrieval":0.23249999999999998,"LEMBQMSumRetrieval":0.16322,"LEMBSummScreenFDRetrieval":0.54801,"LEMBWikimQARetrieval":0.46228} scoresByTaskType {"Retrieval":0.29811499999999996} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label sentence-transformers/all-MiniLM-L6-v2 Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/138` | | | | | 13 | [all-MiniLM-L12-v2](https://benchize.com/models/all-minilm-l12-v2.md) | 0.25source score | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_task` \| 0.25262999999999997 \| source_score \| source_published_aggregate \| Higher is better \| \| `mean_task_type` \| 0.25262999999999997 \| source_score \| source_published_aggregate \| Higher is better \| ### Configuration zeroShotPct 100 ### Reported statistics experiments Not reported rank 147 scoresByTask {"LEMBNarrativeQARetrieval":0.19635,"LEMBNeedleRetrieval":0.1225,"LEMBPasskeyRetrieval":0.1475,"LEMBQMSumRetrieval":0.1308,"LEMBSummScreenFDRetrieval":0.46981,"LEMBWikimQARetrieval":0.44882} scoresByTaskType {"Retrieval":0.25262999999999997} trainedOnTasks Not reported ### Source [Original source](https://mteb-leaderboard-backend.hf.space/v1/benchmarks/LongEmbed/scores) Source MTEB Original model label sentence-transformers/all-MiniLM-L12-v2 Observed 2026-10-21T16:40:31.460Z Evidence SHA-256 `f15d7a6a931cf287269b9fe1060d2ae3f8cd2d1cc004a12b65bfc447716cc008` Source locator `/rows/146` | | | | --- Cite as: LongEmbed · Long-context Retrieval — Benchize, https://benchize.com/benchmarks/mteb%3ALongEmbed (retrieved 2026-10-21)