Evaluating Nova 2.0 Lite model under Amazon's Frontier Model Safety Framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Krishna, Satyapriya, Memelli, Matteo, Wang, Tong, Mohanty, Abhinav, Rajkumar, Claire O'Brien, Motwani, Payal, Gupta, Rahul, Matsoukas, Spyros
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912851801669632
author Krishna, Satyapriya
Memelli, Matteo
Wang, Tong
Mohanty, Abhinav
Rajkumar, Claire O'Brien
Motwani, Payal
Gupta, Rahul
Matsoukas, Spyros
author_facet Krishna, Satyapriya
Memelli, Matteo
Wang, Tong
Mohanty, Abhinav
Rajkumar, Claire O'Brien
Motwani, Payal
Gupta, Rahul
Matsoukas, Spyros
contents Amazon published its Frontier Model Safety Framework (FMSF) as part of the Paris AI summit, following which we presented a report on Amazon's Premier model. In this report, we present an evaluation of Nova 2.0 Lite. Nova 2.0 Lite was made generally available from amongst the Nova 2.0 series and is one of its most capable reasoning models. The model processes text, images, and video with a context length of up to 1M tokens, enabling analysis of large codebases, documents, and videos in a single prompt. We present a comprehensive evaluation of Nova 2.0 Lite's critical risk profile under the FMSF. Evaluations target three high-risk domains-Chemical, Biological, Radiological and Nuclear (CBRN), Offensive Cyber Operations, and Automated AI R&D-and combine automated benchmarks, expert red-teaming, and uplift studies to determine whether the model exceeds release thresholds. We summarize our methodology and report core findings. We will continue to enhance our safety evaluation and mitigation pipelines as new risks and capabilities associated with frontier models are identified.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19134
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Evaluating Nova 2.0 Lite model under Amazon's Frontier Model Safety Framework
Krishna, Satyapriya
Memelli, Matteo
Wang, Tong
Mohanty, Abhinav
Rajkumar, Claire O'Brien
Motwani, Payal
Gupta, Rahul
Matsoukas, Spyros
Cryptography and Security
Software Engineering
Amazon published its Frontier Model Safety Framework (FMSF) as part of the Paris AI summit, following which we presented a report on Amazon's Premier model. In this report, we present an evaluation of Nova 2.0 Lite. Nova 2.0 Lite was made generally available from amongst the Nova 2.0 series and is one of its most capable reasoning models. The model processes text, images, and video with a context length of up to 1M tokens, enabling analysis of large codebases, documents, and videos in a single prompt. We present a comprehensive evaluation of Nova 2.0 Lite's critical risk profile under the FMSF. Evaluations target three high-risk domains-Chemical, Biological, Radiological and Nuclear (CBRN), Offensive Cyber Operations, and Automated AI R&D-and combine automated benchmarks, expert red-teaming, and uplift studies to determine whether the model exceeds release thresholds. We summarize our methodology and report core findings. We will continue to enhance our safety evaluation and mitigation pipelines as new risks and capabilities associated with frontier models are identified.
title Evaluating Nova 2.0 Lite model under Amazon's Frontier Model Safety Framework
topic Cryptography and Security
Software Engineering
url https://arxiv.org/abs/2601.19134