Developer
Amazon
8 indexed models; 5 currently meet the evidence threshold for the overall ranking. Together they have results from 10 evaluations.
Models by Amazon
| Model | Evals | Components | Rank | Release date |
|---|---|---|---|---|
| Nova Lite | 6 | 6/7 | 52 | 2024-12-03 |
| Nova 2.0 Lite | 4 | 2/7 | 129 | — |
| Nova Premier | 4 | 5/7 | 153 | — |
| Nova Micro | 6 | 5/7 | 171 | — |
| Nova Pro | 7 | 6/7 | 242 | 2024-12-03 |
| Amazon Nova Experimental Chat | 1 | 1/7 | — | — |
| Nova 2.0 Omni | 1 | 1/7 | — | — |
| Nova 2.0 Pro | 1 | 1/7 | — | — |
Evaluations covering Amazon models (10)
AA-Omniscience · AgentDrive Safety Compliance · AILuminate General Purpose AI Chat · Arena Factuality — Text Arena (factuality-only weighting) · Cisco AI Defense Rolling Single-Turn Leaderboard · Confabulations · Enkrypt AI Safety Leaderboard · RefusalBench · SpeciEval · Vectara HHEM Factual Consistency