16 listings across 8 models
Data policies
from the provider's published policiesHeadquarters: GBPrivacy policyTerms of service
- On training
Sference shall not use Customer Content (including Customer Personal Data) to train, retrain, or improve any machine learning model of Sference or of any third party, except: (a) where and to the extent expressly instructed or agreed by Customer in writing (for example, a fine-tuning job submitted by Customer for Customer's own model, or a training arrangement specifically agreed in respect of paid Services); or (b) in respect of Services expressly designated by Sference as free of charge, where and to the extent the applicable service terms disclose such use and Customer elects to use those Services.
Possible sources (2)
- On keeping your data
Inference inputs and outputs are not retained longer than operationally necessary as described in Annex 1.
Possible sources (2)
- On where data is processed
Sference Processes Customer Content on inference and storage infrastructure located within the EEA, as described in Annex 2.
More from Sference on where data is processed (1)
Inference and storage of customer content run on infrastructure located within the EEA; ancillary vendors (analytics, monitoring, email, payments, status notifications, productivity tools) never receive inference content.
Possible sources (2)
- Other statements
Operating entity: Neural Compute Ltd (trading as Sference), company number 17195150, registered office 167-169 Great Portland Street, 5th Floor, London, England, W1W 5PF.
Possible sources (2)
We take these statements from Sference's own published policies each time we refresh the data, so they can change or disappear when those pages do. Check with the provider before you rely on any of this.
Sold by Sference
8 listings sold by Sference.
Default order. Select a score for details.
About these columns
- llminfo IQ
- llminfo IQ (capability index). How llminfo IQ is computed
- Coding IQ
- llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
- Value
- Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
- Yap
- Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
- Epoch Capabilities Index
- Epoch Capabilities Index benchmark details
Run by Sference
8 listings where Sference runs the model. Another provider sells these listings.
Default order. Select a score for details.
About these columns
- llminfo IQ
- llminfo IQ (capability index). How llminfo IQ is computed
- Coding IQ
- llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
- Value
- Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
- Yap
- Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
- Epoch Capabilities Index
- Epoch Capabilities Index benchmark details
Showing 5 of 8: one listing for each model.
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)