Nova 2 Lite: benchmark results
Provider: Amazon. Released 2025-08-01. Access: API.
Unified ELO 1546 ± 1, rank #455 of 1392 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (Multi-Challenge) | 76.6 | Score (%) | 96.4 |
| BenchmarkList ECI | 119.71 | Capability Index (ECI) | 61.5 |
| ZeroEval GPQA Diamond | 79.6 | GPQA Diamond Score | 59.8 |
| LLM Stats Score | 25.55 | LLM Stats Score (conservative rating) | 58.4 |
| LM Market Cap LMC Score | 60.4 | LMC Score (0-100) | 51.2 |
| AI for Education Pedagogy - Maths | 73.81 | Accuracy (%) | 42 |
| AI for Education SEND | 67.89 | Accuracy (%) | 30.5 |
| AI for Education Pedagogy - Secondary | 69.03 | Accuracy (%) | 26.9 |
| AI for Education Pedagogy | 69.63 | Accuracy (%) | 26.1 |
| AI for Education Pedagogy - Science | 69.4 | Accuracy (%) | 26.1 |
| AI for Education Pedagogy - Primary | 73.24 | Accuracy (%) | 25.6 |
| AI for Education Pedagogy - Social studies | 66.36 | Accuracy (%) | 25.6 |
Interactive version: theaggregate.ai/model?slug=nova-2-lite · How It Works · Data refreshed daily, snapshot 2026-09-05.