Ai Sage model product
Giga-Embeddings-instruct
Giga-Embeddings-instruct is an embedding model from Ai Sage.
Updated Oct 23, 2026. Default version: Giga-Embeddings-instruct
LLMBoard Embedding Score80.1Giga-Embeddings-instruct
Coverage85%5 benchmark families
Context window4.1KTokens
Official input priceN/AOfficial price unavailable
Giga-Embeddings-instruct Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Giga-Embeddings-instruct Benchmark Results
Benchmark scores for Giga-Embeddings-instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMTEB English v2 Reranking | Score49.72% | Rank21 | Participants244 | Percentile91.77% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Classification | Score88.39% | Rank25 | Participants261 | Percentile90.77% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Retrieval | Score59.68% | Rank26 | Participants218 | Percentile88.48% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Clustering | Score56.19% | Rank32 | Participants221 | Percentile85.91% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Semantic Similarity | Score82.92% | Rank58 | Participants215 | Percentile73.36% | EvidenceA | EvaluatedN/A |
Giga-Embeddings-instruct 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.
Giga-Embeddings-instruct 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.
Giga-Embeddings-instruct Runtime Performance
Provider-specific output speed and catalog latency for Giga-Embeddings-instruct. 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.
Giga-Embeddings-instruct Specifications
Technical details for the model's default version.
- Version
- Giga-Embeddings-instruct
- Released
- Sep 23, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 3.2B
- Context window
- 4.1K
- Max output
- N/A
- Inputs
- text
- Outputs
- embedding
- Open weights
- Yes
- License
- mit
Giga-Embeddings-instruct 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 |
|---|
| VersionGiga-Embeddings-instruct | Released | LLMBoard80.07 | Parameters3.2B | Context4.1K | Max outputN/A | Open weightsYes | Licensemit |
Models similar to Giga-Embeddings-instruct
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3-Embedding-0.6B
Alibaba Cloud / Qwen Team
What is Giga-Embeddings-instruct?
Key information about Giga-Embeddings-instruct and its available data.
Giga-Embeddings-instruct is an embedding model from Ai Sage. It is a ranked model from MTEB.
Data as of 2026-10-22.
FAQ
Common questions about Giga-Embeddings-instruct.
When was Giga-Embeddings-instruct released?
Giga-Embeddings-instruct's default version was released on Sep 23, 2025.
How much does Giga-Embeddings-instruct cost?
No official standard PAYG price is currently available for Giga-Embeddings-instruct.
Who created Giga-Embeddings-instruct?
Giga-Embeddings-instruct was created by Ai Sage.
What is the context window for Giga-Embeddings-instruct?
The default version has a 4.1K token context window.
Is Giga-Embeddings-instruct open weight?
Yes. The default version is marked as open weight under mit.