Apps & data pipelines
Scira's open Amos 1 family offers small and large models for decisions about text and images, with answer types and object-box support varying by model.
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
The Apache-2.0 family includes a hosted demonstration. Headline comparisons come from author-run or submitted results, not independently verified rankings. Larger variants exceed some Jev-class cost limits. A comparison therefore needs to account for model size, serving hardware and the benchmark's rules.
Choose the size and input type from the collection, then try a question with clearly allowed answers. To compare with Jev, use the same test set and cost rules. Results on the public subset cannot stand in for a score on the full benchmark.