Amazon model product
Amazon Nova 2 Omni is Amazon's first unified multimodal reasoning model that processes text, documents, images, video, and audio inputs and generates both text and images from a single model, eliminating multi-model coordination complexity.
Updated Aug 12, 2026. Default version: Nova 2 Omni
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Nova 2 Omni.
| CoVoST2 | 40.7% | 01 | 4 | 100.0% | C | |
| MAVERIX | 66.6% | 01 | 1 | 100.0% | C | |
| MMAU | 75.3% | 01 | 2 | 100.0% | C | |
| RefCOCOg | 86.3% | 01 | 1 | 100.0% | C | |
| QVHighlights | 76.7% | 02 | 3 | 50.0% | C | |
| Tau2 Airline | 68.8% | 02 | 23 | 95.5% | C | |
| Multi-Challenge | 75.5% | 03 | 29 | 92.9% | C | |
| RealKIE-FCC | 59.8% | 03 | 3 | 0.0% | C | |
| OCRBench_V2 | 58.2% | 05 | 7 | 33.3% | C | |
| Tau2 Retail | 78.3% | 09 | 26 | 68.0% | C | |
| BFCL-V4 | 58.3% | 10 | 13 | 25.0% | C | |
| Video-MME | 77.9% | 10 | 17 | 43.8% | C | |
| ScreenSpot | 85.4% | 14 | 16 | 13.3% | C | |
| IFBench | 68.7% | 22 | 29 | 25.0% | C | |
| Tau2 Telecom | 80.0% | 22 | 35 | 38.2% | C | |
| AIME 2025 | 92.1% | 38 | 114 | 67.3% | C | |
| MMMU-Pro | 61.4% | 47 | 66 | 29.2% | C | |
| MMLU-Pro | 80.7% | 50 | 129 | 61.7% | C |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Provider-specific output speed and catalog latency for Nova 2 Omni. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Official vendor API pricing appears first, followed by individual provider offers.
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Available versions of this model. The score column identifies the version used in the overall ranking.
| Nova 2 Omni | 43.9 | N/A | N/A | N/A | No | Proprietary |
Key information about Nova 2 Omni and its available data.
Amazon Nova 2 Omni is Amazon's first unified multimodal reasoning model that processes text, documents, images, video, and audio inputs and generates both text and images from a single model, eliminating multi-model coordination complexity.
It delivers strong multimodal perception, core reasoning, agentic tool use, and high-quality image generation and editing, with configurable extended thinking. It supports a 1M token context window, 200+ languages for text, and 10 languages for speech input.
Data as of 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about Nova 2 Omni.
Nova 2 Omni's default version was released on Dec 2, 2025.
No official standard PAYG price is currently available for Nova 2 Omni.
Nova 2 Omni was created by Amazon.
A context window is not available for the default version.
No. The default version is not marked as having publicly available weights.
No provider offering is currently linked to the default version.
Nearby ranked alternatives include DeepSeek-R1, GPT-OSS-120B, MiniMax M2.