Evaluator Bench
Amazon (arXiv), 2026-01; retrieved 2026-09-15 tier 4 press (primary)confirmed

Evaluating Nova 2.0 Lite model under Amazon's Frontier Model Safety Framework (arXiv 2601.19134v1, HTML)

https://arxiv.org/html/2601.19134v1

Amazon's report on Nova 2.0 Lite: "we worked with Nemesys Insights to conduct a large-scale, independent uplift study" with nearly 800 participants. Lab document; typed press primary. Normalizer gets HTTP 406; fetched via curl 2026-09-15; span present.

Signals citing this source

  • Nemesys Insights, X (against): Consults for a lab.“we worked with Nemesys Insights to conduct a large-scale, independent uplift study”

Ledger rows citing this URL

  • none