Amazon logo

Nova 2 Omni

Multimodal
Amazon

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.

Key Specifications

Parameters
-
Context
-
Release Date
December 2, 2025
Average Score
71.7%

Timeline

Key dates in the model's history
Announcement
December 2, 2025
Last Update
August 29, 2026

Technical Specifications

Parameters
-
Training Tokens
-
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval

Benchmark Results

Model performance metrics across various tests and benchmarks

Other Tests

Specialized benchmarks
AIME 2025
accuracySelf-reported
92.1%
BFCL-V4
overall FC accuracySelf-reported
58.3%
CoVoST2
BLEU (X-to-English)Self-reported
40.7%
IFBench
prompt loose accuracySelf-reported
68.7%
MAVERIX
accuracySelf-reported
66.6%
MMAU
average accuracy (speech, sound, music)Self-reported
75.3%
MMLU-Pro
accuracySelf-reported
80.7%
MMMU-Pro
accuracySelf-reported
61.4%
Multi-Challenge
accuracySelf-reported
75.5%
OCRBench_V2
avg accuracySelf-reported
58.2%
QVHighlights
R1@0.5Self-reported
76.7%
RealKIE-FCC
ANLS (Verified)Self-reported
59.8%
RefCOCOg
acc@0.5Self-reported
86.3%
ScreenSpot
point accuracySelf-reported
85.4%
Tau2 Airline
Verified avg@3Self-reported
68.8%
Tau2 Retail
Verified avg@3Self-reported
78.3%
Tau2 Telecom
avg@3 (Artificial Analysis)Self-reported
80.0%
Video-MME
accuracySelf-reported
77.9%

License & Metadata

License
proprietary
Announcement Date
December 2, 2025
Last Updated
August 29, 2026

Similar Models

All Models

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.