Google model product
embeddinggemma-2
embeddinggemma-2 is an embedding model from Google ranked on MTEB.
Updated Oct 23, 2026. Default version: embeddinggemma-2
LLMBoard Embedding Score62.6embeddinggemma-2
Coverage85%5 benchmark families
Context window8.2KTokens
Official input priceN/AOfficial price unavailable
embeddinggemma-2 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
embeddinggemma-2 Benchmark Results
Benchmark scores for embeddinggemma-2.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMTEB English v2 Classification | Score87.60% | Rank32 | Participants261 | Percentile88.08% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Clustering | Score51.70% | Rank48 | Participants221 | Percentile78.64% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Semantic Similarity | Score82.75% | Rank67 | Participants215 | Percentile69.16% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Retrieval | Score51.33% | Rank106 | Participants218 | Percentile51.61% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Reranking | Score46.03% | Rank134 | Participants244 | Percentile45.27% | EvidenceA | EvaluatedN/A |
embeddinggemma-2 Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
embeddinggemma-2 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
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.
embeddinggemma-2 Runtime Performance
Provider-specific output speed and catalog latency for embeddinggemma-2. Runtime does not affect the capability score.
No runtime data
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.
embeddinggemma-2 Specifications
Technical details for the model's default version.
- Version
- embeddinggemma-2
- Released
- Oct 6, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 271M
- Context window
- 8.2K
- Max output
- N/A
- Inputs
- text, image, audio, video
- Outputs
- embedding
- Open weights
- Yes
- License
- gemma
embeddinggemma-2 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| Versionembeddinggemma-2 | Released | LLMBoard62.62 | Parameters271M | Context8.2K | Max outputN/A | Open weightsYes | Licensegemma |
Models similar to embeddinggemma-2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
siglip-large-patch16-256
GOGoogle
text-multilingual-embedding-002
GOGoogle
siglip-so400m-patch14-384
GOGoogle
embeddinggemma-300m
GOGoogle
siglip-large-patch16-384
GOGoogle
text-embedding-004
What is embeddinggemma-2?
Key information about embeddinggemma-2 and its available data.
embeddinggemma-2 is a Google embedding model that is ranked on MTEB.
Data as of 2026-10-22.
FAQ
Common questions about embeddinggemma-2.
When was embeddinggemma-2 released?
embeddinggemma-2's default version was released on Oct 6, 2026.
How much does embeddinggemma-2 cost?
No official standard PAYG price is currently available for embeddinggemma-2.
Who created embeddinggemma-2?
embeddinggemma-2 was created by Google.
What is the context window for embeddinggemma-2?
The default version has a 8.2K token context window.
Is embeddinggemma-2 open weight?
Yes. The default version is marked as open weight under gemma.
How many API providers offer embeddinggemma-2?
No provider offering is currently linked to the default version.