Nova 2 Lite — benchmark results
Provider: Amazon. Released 2025-08-01. Access: API.
Unified ELO 1359 ± 116, rank #1386 of 1776 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (Multi-Challenge) | 76.6 | Score (%) | 96.4 |
| ZeroEval GPQA Diamond | 79.6 | GPQA Diamond Score | 61.7 |
| AI for Education Pedagogy - Maths | 73.81 | Accuracy (%) | 45.5 |
| AI for Education SEND | 67.89 | Accuracy (%) | 32.8 |
| AI for Education Pedagogy - Secondary | 69.03 | Accuracy (%) | 29.1 |
| AI for Education Pedagogy | 69.63 | Accuracy (%) | 28.2 |
| AI for Education Pedagogy - Science | 69.4 | Accuracy (%) | 28.2 |
| AI for Education Pedagogy - Primary | 73.24 | Accuracy (%) | 27.7 |
| AI for Education Pedagogy - Social studies | 66.36 | Accuracy (%) | 27.7 |
| AI for Education Pedagogy - Technology | 72.64 | Accuracy (%) | 27 |
| ALE-Bench | 236.25 | Performance (Self-Refine x1) (self-reported) | 7.7 |
| LLM Stats (MCP Atlas) | 24.6 | Score (%) | 0 |
Interactive version: theaggregate.ai/model?slug=nova-2-lite · How the rankings work · Data refreshed daily, snapshot 2026-07-22.