Amazon model product
Amazon Nova 2 Pro is Amazon's highest-intelligence model for complex workloads, simultaneously processing text, documents, images, video, and audio for large-scale multimodal reasoning.
Updated Aug 12, 2026. Default version: Nova 2 Pro
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 Pro.
| Multi-Challenge | 0.8 | 1 | 29 | 100.0% | C | |
| RealKIE-FCC | 0.7 | 1 | 3 | 100.0% | C | |
| LongCodeBench | 0.8 | 2 | 2 | 0.0% | C | |
| OCRBench_V2 | 0.6 | 2 | 7 | 83.3% | C | |
| QVHighlights | 0.8 | 3 | 3 | 0.0% | C | |
| IFBench | 0.8 | 4 | 29 | 89.3% | C | |
| Terminal-Bench | 0.4 | 6 | 25 | 79.2% | C | |
| Tau2 Airline | 0.7 | 7 | 23 | 72.7% | C | |
| BFCL-V4 | 0.6 | 8 | 13 | 41.7% | C | |
| ScreenSpot | 0.9 | 12 | 16 | 26.7% | C | |
| Tau2 Retail | 0.8 | 13 | 26 | 52.0% | C | |
| Tau2 Telecom | 0.9 | 14 | 35 | 61.8% | C | |
| LiveCodeBench | 0.7 | 15 | 73 | 80.6% | C | |
| AIME 2025 | 0.9 | 36 | 114 | 69.0% | C | |
| MMLU-Pro | 0.8 | 42 | 129 | 68.0% | C | |
| MMMU-Pro | 0.6 | 43 | 66 | 35.4% | C | |
| SWE-Bench Verified | 0.7 | 60 | 105 | 43.3% | C | |
| GPQA | 0.8 | 78 | 234 | 67.0% | C |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
| Nova | nova-2-pro-v1 | global | N/A | N/A | 1M |
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 Pro | 52.5 | N/A | N/A | N/A | No | Proprietary |
Key information about Nova 2 Pro and its available data.
Amazon Nova 2 Pro is Amazon's highest-intelligence model for complex workloads, simultaneously processing text, documents, images, video, and audio for large-scale multimodal reasoning.
It features hybrid reasoning with configurable extended thinking and excels at high-accuracy tasks, multi-step planning, long-document analysis, advanced math, and autonomous agentic and software-engineering tasks. 5 Pro/Gemini 3 Pro across broad benchmarks.
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 Pro.
Nova 2 Pro's default version was released on Dec 2, 2025.
No official standard PAYG price is currently available for Nova 2 Pro.
Nova 2 Pro 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.
1 provider offerings are linked to the default version.
Nearby ranked alternatives include MiMo V2 Omni, Gemma 4 26B A4B, o3.