SYSTEM ACTIVE
Home›Models›Nova Pro

Nova Pro

Amazon

86·Strong

Overall Trust Score

Amazon's Nova Pro model integrated with AWS services. Designed for enterprise customers requiring seamless AWS integration with good general capabilities.

aws
enterprise
hipaa-eligible
fedramp
compliance
integrated
Version: 2025-01
Last Evaluated: November 8, 2025
Official Website →

Trust Vector

Performance & Reliability

73

Moderate performance with excellent AWS integration. Large 300K context window. Reliable AWS infrastructure.

task accuracy code
70
Methodology
Coding benchmarks
Evidence
AWS Documentation
~38% HumanEval (estimated)
Date: 2025-01-15
Confidence: mediumLast verified: 2025-11-08
task accuracy reasoning
72
Methodology
Mathematical reasoning
Evidence
AWS Benchmarks
~50% MATH
Date: 2025-01-15
Confidence: mediumLast verified: 2025-11-08
task accuracy general
74
Methodology
Knowledge testing
Evidence
MMLU Benchmark
46.9% on multitask understanding
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
output consistency
75
Methodology
Internal testing
Evidence
AWS Internal Testing
Good consistency
Date: 2025-01-15
Confidence: mediumLast verified: 2025-11-08
latency p50
Value: 1.0s
Methodology
AWS infrastructure
Evidence
AWS Documentation
~1.0s typical
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
latency p95
Value: 2.0s
Methodology
CloudWatch metrics
Evidence
AWS CloudWatch
p95 ~2.0s
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
context window
Value: 300,000 tokens
Methodology
Official specification
Evidence
AWS Documentation
300K context
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
uptime
99
Methodology
AWS service SLA
Evidence
AWS SLA
99.9% SLA
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08

Security

89

Excellent security leveraging AWS infrastructure. Strong IAM and VPC integration.

prompt injection resistance
87
Methodology
AWS security testing
Evidence
AWS Security Testing
Strong resistance
Date: 2025-01-15
Confidence: mediumLast verified: 2025-11-08
jailbreak resistance
88
Methodology
Safety testing
Evidence
AWS Safety
Robust guardrails
Date: 2025-01-15
Confidence: mediumLast verified: 2025-11-08
data leakage prevention
92
Methodology
Policy analysis
Evidence
AWS Privacy
No training on customer data
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
output safety
88
Methodology
Safety benchmarks
Evidence
AWS Guardrails
Comprehensive content filtering
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
api security
93
Methodology
Security architecture review
Evidence
AWS IAM
AWS IAM integration, VPC support
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08

Privacy & Compliance

93

Exceptional privacy with AWS infrastructure. HIPAA eligible, FedRAMP authorized. Zero data retention.

data residency
Value: Multi-region (AWS)
Methodology
AWS infrastructure review
Evidence
AWS Regions
Available in all major AWS regions
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
training data optout
95
Methodology
Privacy policy
Evidence
AWS Privacy
No training on customer data
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
data retention
Value: 0 days (ephemeral)
Methodology
Documentation review
Evidence
AWS Documentation
Ephemeral processing
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
pii handling
90
Methodology
Feature review
Evidence
AWS Guardrails
PII detection and redaction available
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
compliance certifications
95
Methodology
Certification verification
Evidence
AWS Compliance
SOC 2, GDPR, HIPAA, FedRAMP
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
zero data retention
95
Methodology
Architecture review
Evidence
AWS Documentation
Zero retention model
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08

Trust & Transparency

81

Good transparency with AWS Guardrails. Comprehensive documentation.

explainability
79
Methodology
Reasoning evaluation
Evidence
Model Behavior
Reasonable explanations
Date: 2025-01-15
Confidence: mediumLast verified: 2025-11-08
hallucination rate
78
Methodology
Factual QA testing
Evidence
AWS Benchmarks
Moderate accuracy
Date: 2025-01-15
Confidence: mediumLast verified: 2025-11-08
bias fairness
80
Methodology
Bias benchmarks
Evidence
AWS Responsible AI
Bias testing applied
Date: 2025-01-15
Confidence: mediumLast verified: 2025-11-08
uncertainty quantification
79
Methodology
Qualitative assessment
Evidence
Model Behavior
Basic uncertainty expression
Date: 2025-01-15
Confidence: mediumLast verified: 2025-11-08
model card quality
87
Methodology
Documentation review
Evidence
AWS Documentation
Good documentation
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
training data transparency
76
Methodology
Public disclosure review
Evidence
AWS Statements
Limited disclosure
Date: 2025-01-15
Confidence: mediumLast verified: 2025-11-08
guardrails
90
Methodology
Feature review
Evidence
AWS Guardrails
Configurable guardrails
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08

Operational Excellence

94

Exceptional operational excellence with full AWS integration. Best-in-class monitoring and support.

api design quality
95
Methodology
API review
Evidence
AWS Bedrock API
Well-designed AWS API
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
sdk quality
96
Methodology
SDK review
Evidence
AWS SDKs
Comprehensive AWS SDKs
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
versioning policy
92
Methodology
Policy review
Evidence
AWS Versioning
AWS standard versioning
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
monitoring observability
97
Methodology
Observability review
Evidence
AWS CloudWatch
Full CloudWatch integration
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
support quality
95
Methodology
Support assessment
Evidence
AWS Support
Enterprise AWS support available
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
ecosystem maturity
94
Methodology
Ecosystem analysis
Evidence
AWS Ecosystem
Full AWS service integration
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08
license terms
93
Methodology
Terms review
Evidence
AWS Terms
Standard AWS terms
Date: 2025-01-15
Confidence: highLast verified: 2025-11-08

✨ Strengths

  • •Seamless AWS ecosystem integration (CloudWatch, IAM, VPC)
  • •Exceptional compliance (HIPAA, FedRAMP, SOC 2)
  • •Very large context window (300K tokens)
  • •Zero data retention with AWS privacy
  • •Enterprise-grade AWS support and SLA
  • •Built-in PII detection and redaction

⚠️ Limitations

  • •Moderate performance (46.9% MMLU)
  • •Limited coding capabilities
  • •AWS vendor lock-in
  • •Higher costs within AWS ecosystem
  • •Performance lags behind specialized models
  • •Best value only for existing AWS customers

📊 Metadata

pricing:
input: $0.80 per 1M tokens (on-demand), $0.40 per 1M tokens (batch)
output: $3.20 per 1M tokens (on-demand), $1.60 per 1M tokens (batch)
notes: AWS Bedrock pricing with 50% batch discount, volume discounts available
last verified: 2025-11-09
context window: 300000
languages:
0: English
1: Spanish
2: French
3: German
4: Italian
5: Portuguese
6: Japanese
7: Korean
8: Chinese
modalities:
0: text
1: image (input)
api endpoint: https://bedrock.{region}.amazonaws.com
open source: false
architecture: Transformer-based
parameters: Not disclosed

Use Case Ratings

code generation

72

Basic coding. Better integrated with AWS CodeWhisperer.

customer support

78

Good for AWS-integrated customer support applications.

content creation

76

Adequate content creation with large context (300K).

data analysis

75

Basic analysis integrated with AWS data services.

research assistant

74

Adequate for research with large context window.

legal compliance

88

Excellent for legal with AWS compliance (HIPAA, FedRAMP).

healthcare

90

Excellent for healthcare with HIPAA eligibility and AWS integration.

financial analysis

82

Good for finance with AWS FinOps integration.

education

76

Adequate for education, better options for STEM.

creative writing

74

Basic creative writing capabilities.

Similar Models

Claude Sonnet 4.5

90

Anthropic

GPT-4.1

85

OpenAI

Amazon Bedrock Agents

90

Amazon Web Services