clustering benchmark
MIEB English Clustering is a clustering benchmark represented by the current MIEB(eng) leaderboard.
Updated Sep 8, 2026
Higher official leaderboard task-type mean ranks better on this benchmark.
Rank | Model | Official leaderboard task-type mean | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelQUEVA02-CLIP-bigE-14-plusQuansun | Official leaderboard task-type mean92.38% | Percentile100.00% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank02 | ModelQUEVA02-CLIP-bigE-14Quansun | Official leaderboard task-type mean89.42% | Percentile97.92% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank03 | ModelQUEVA02-CLIP-L-14Quansun | Official leaderboard task-type mean88.27% | Percentile95.83% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank04 | ModelLACLIP-ViT-L-14-DataComp.XL-s13B-b90KLaion | Official leaderboard task-type mean86.44% | Percentile93.75% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank05 | ModelJIjina-embeddings-v5-omni-smallJinaai | Official leaderboard task-type mean86.01% | Percentile91.67% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank06 | ModelLACLIP-ViT-bigG-14-laion2B-39B-b160kLaion | Official leaderboard task-type mean85.59% | Percentile89.58% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank07 | ModelLACLIP-ViT-H-14-laion2B-s32B-b79KLaion | Official leaderboard task-type mean83.86% | Percentile87.50% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank08 | ModelNAnomic-embed-vision-v1.5Nomic Ai | Official leaderboard task-type mean83.64% | Percentile85.42% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank09 | ModelLACLIP-ViT-L-14-laion2B-s32B-b82KLaion | Official leaderboard task-type mean83.50% | Percentile83.33% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank10 | ModelFAdinov2-largeFacebook | Official leaderboard task-type mean83.10% | Percentile81.25% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank11 | ModelFAdinov2-baseFacebook | Official leaderboard task-type mean82.74% | Percentile79.17% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank12 | ModelLACLIP-ViT-g-14-laion2B-s34B-b88KLaion | Official leaderboard task-type mean82.74% | Percentile77.08% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank13 | ModelQUEVA02-CLIP-B-16Quansun | Official leaderboard task-type mean82.55% | Percentile75.00% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank14 | ModelVOvoyage-multimodal-3Voyageai | Official leaderboard task-type mean82.41% | Percentile72.92% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank15 | ModelGO | Official leaderboard task-type mean82.13% | Percentile70.83% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank16 | ModelGO | Official leaderboard task-type mean82.11% | Percentile68.75% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank17 | ModelLACLIP-ViT-B-16-DataComp.XL-s13B-b90KLaion | Official leaderboard task-type mean81.73% | Percentile66.67% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank18 | ModelFAdinov2-giantFacebook | Official leaderboard task-type mean81.44% | Percentile64.58% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank19 | ModelFAdinov2-smallFacebook | Official leaderboard task-type mean80.20% | Percentile62.50% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank20 | ModelGO | Official leaderboard task-type mean79.94% | Percentile60.42% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank21 | ModelDNDNA-VL-STEER-2BDnotitia | Official leaderboard task-type mean78.88% | Percentile58.33% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank22 | ModelLACLIP-ViT-B-32-laion2B-s34B-b79KLaion | Official leaderboard task-type mean77.99% | Percentile56.25% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank23 | ModelSAblip-itm-large-cocoSalesforce | Official leaderboard task-type mean77.53% | Percentile54.17% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank24 | ModelLACLIP-ViT-B-32-DataComp.XL-s13B-b90KLaion | Official leaderboard task-type mean77.37% | Percentile52.08% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank25 | ModelSAblip-itm-large-flickrSalesforce | Official leaderboard task-type mean76.43% | Percentile50.00% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank26 | ModelOP | Official leaderboard task-type mean76.41% | Percentile47.92% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank27 | ModelGO | Official leaderboard task-type mean76.27% | Percentile45.83% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank28 | ModelBAbge-visualized-baseBaai | Official leaderboard task-type mean76.19% | Percentile43.75% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank29 | ModelGO | Official leaderboard task-type mean75.24% | Percentile41.67% | Participants49 | EvidenceA | EvaluatedN/A |
| Rank30 | ModelGO | Official leaderboard task-type mean74.65% | Percentile39.58% | Participants49 | EvidenceA | EvaluatedN/A |
The leading models and scores on this benchmark.
A closer view of the leading scores on this benchmark.
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What MIEB English Clustering measures and how its scores work.
MIEB English Clustering is a clustering benchmark.
It reports the Official leaderboard task-type mean in ratio units.
Scores are shown in ratio. This benchmark is verified and has an evidence level of A.
MTEB. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about MIEB English Clustering.
EVA02-CLIP-bigE-14-plus is currently ranked first with 92.38%.
The current leaders are EVA02-CLIP-bigE-14-plus (92.38%), EVA02-CLIP-bigE-14 (89.42%), and EVA02-CLIP-L-14 (88.27%).
No matched official input price is currently available.
No matched runtime record is currently available.
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.
It reports the Official leaderboard task-type mean in ratio units.
Yes. Higher values rank better for this benchmark.
49 model results are currently shown.
No. This benchmark is shown for reference but does not contribute to the overall score.
Ranking basisThis mieb english clustering AI model leaderboard uses descending official leaderboard task-type mean in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
Selection summary
EVA02-CLIP-bigE-14-plus currently leads MIEB English Clustering with 92.38%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.