Facebook model product
dinov2-base
dinov2-base is a Facebook embedding model ranked by MTEB.
Updated Sep 8, 2026. Default version: dinov2-base
LLMBoard Embedding Score53.9dinov2-base
Coverage45%3 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
dinov2-base Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
dinov2-base Benchmark Results
Benchmark scores for dinov2-base.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMIEB English Classification | Score76.62% | Rank06 | Participants49 | Percentile89.58% | EvidenceA | EvaluatedN/A |
| BenchmarkMIEB English Clustering | Score82.74% | Rank11 | Participants49 | Percentile79.17% | EvidenceA | EvaluatedN/A |
| BenchmarkMIEB English Semantic Similarity | Score16.83% | Rank45 | Participants50 | Percentile10.20% | EvidenceA | EvaluatedN/A |
dinov2-base 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.
dinov2-base 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.
dinov2-base Runtime Performance
Provider-specific output speed and catalog latency for dinov2-base. 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.
dinov2-base Specifications
Technical details for the model's default version.
- Version
- dinov2-base
- Released
- Jul 18, 2023
- Knowledge cutoff
- Unknown
- Parameters
- 87M
- Context window
- N/A
- Max output
- N/A
- Inputs
- image
- Outputs
- embedding
- Open weights
- Yes
- License
- apache-2.0
dinov2-base 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 |
|---|
| Versiondinov2-base | Released | LLMBoard53.93 | Parameters87M | ContextN/A | Max outputN/A | Open weightsYes | Licenseapache-2.0 |
Models similar to dinov2-base
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
text-embedding-3-small
OpenAI
What is dinov2-base?
Key information about dinov2-base and its available data.
dinov2-base is an embedding model from Facebook. It is listed as a ranked model from MTEB.
Data as of 2026-09-08.
FAQ
Common questions about dinov2-base.
When was dinov2-base released?
dinov2-base's default version was released on Jul 18, 2023.
How much does dinov2-base cost?
No official standard PAYG price is currently available for dinov2-base.
Who created dinov2-base?
dinov2-base was created by Facebook.
What is the context window for dinov2-base?
A context window is not available for the default version.
Is dinov2-base open weight?
Yes. The default version is marked as open weight under apache-2.0.
How many API providers offer dinov2-base?
No provider offering is currently linked to the default version.