Amazon
2 ranked models in a catalog of 5 text models. Nova Pro leads this lab at #131 overall.
Ranked models
Global ranks · current snapshot| Rank | Model | SI Score | coding | math | reasoning | preference | Confidence | Blended price | Context | Released |
|---|---|---|---|---|---|---|---|---|---|---|
| #131 | Nova Pro | 37.4 | — | — | 4.4 | 57.3 | 100% | — | 300K | Dec 3, 2024 |
| #134 | Nova Lite | 36.6 | — | — | 3.6 | 53.6 | 100% | — | 300K | Dec 3, 2024 |
Pillars use a 0–100 scale. * marks an imputed neutral prior where the model has no scored results in that pillar; it is not a measured benchmark result. Prices are USD per 1M tokens; see the blend and price comparison.
Scores and releases
Provisional models
3 awaiting rank-eligible evidence- Nova 2 Lite
Results cover 1 pillar; at least 2 required
- Nova Premier
No usable open benchmark results found
- Nova Micro
Results cover 1 pillar; at least 2 required
Latest Amazon news
All AI news ↗Pay-per-inference for AI agents: How BlockRun and Incarna use Amazon Bedrock AgentCore payments
Share GPU clusters across teams with isolation and fairness using Amazon SageMaker HyperPod
Introducing Claude Haiku 5.5 on AWS
Rethinking access control for RAG with Amazon Quick and Amazon Bedrock
Beyond hours saved: Building the business case for agentic automation
How Qlik built grounded, enterprise-scale AI with Amazon Bedrock