Cointegrated model product
LaBSE-en-ru is an embedding model from Cointegrated that is ranked in MTEB.
Updated Sep 8, 2026. Default version: LaBSE-en-ru
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for LaBSE-en-ru.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMTEB English v2 Semantic Similarity | Score70.13% | Rank189 | Participants211 | Percentile10.48% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Clustering | Score36.70% | Rank191 | Participants217 | Percentile12.04% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Retrieval | Score16.58% | Rank196 | Participants212 | Percentile7.58% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Reranking | Score41.12% | Rank213 | Participants241 | Percentile11.67% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Classification | Score72.49% | Rank222 | Participants257 | Percentile13.67% | EvidenceA | EvaluatedN/A |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for LaBSE-en-ru. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionLaBSE-en-ru | Released | LLMBoard17.11 | Parameters129M | Context512 | Max outputN/A | Open weightsYes | Licensenot specified |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about LaBSE-en-ru and its available data.
LaBSE-en-ru is an embedding model from Cointegrated. It is listed as a ranked model in MTEB.
Data as of 2026-09-08.
Common questions about LaBSE-en-ru.
LaBSE-en-ru's default version was released on Jun 10, 2021.
No official standard PAYG price is currently available for LaBSE-en-ru.
LaBSE-en-ru was created by Cointegrated.
The default version has a 512 token context window.
Yes. The default version is marked as open weight under not specified.
No provider offering is currently linked to the default version.