Nova 2.0 Lite (Low): benchmark results

Provider: Amazon. Released 2025-12-02. Access: API.

Unified ELO 1548 ± 1, rank #990 of 3078 rated models, from 41 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA IFBench61.22Accuracy (%)72.4
Tau2-Bench Telecom71.93Success Rate (%)65.7
AA TAU-2 Bench71.93Accuracy (%)64.1
AA MMLU-Pro78.78Accuracy (%)61.5
AA LiveCodeBench46.88Pass@1 (%)53.5
Artificial Analysis Intelligence Index11.8Intelligence Index51.2
AA Long Context Reasoning54.33Accuracy (%)50.1
AA GPQA Diamond69.8Accuracy (%)47.7
Sonar LLM Leaderboard - Java - Bug Density0.92Bugs per 1,000 lines of code (lower is better)47.2
Sonar LLM Leaderboard - Java - Pass Rate76.26Passing tests (%)45.8
AA AIME 202546.67Accuracy (%)45.6
AA-Omniscience Index - Software Engineering (SWE) - HTML-28Omniscience Index45.4

Interactive version: theaggregate.ai/model?slug=nova-2-0-lite-low · How It Works · Data refreshed daily, snapshot 2026-09-19.