Model

Amazon Nova Pro

CLOSED

Amazon · Amazon Nova family · released Dec 3, 2024

Highest-accuracy multimodal Nova at launch; workhorse mid/high tier for complex text, image and video tasks before Premier arrived.

ReasoningCodingVisionFunction callingTool useAgentic

1216.3

Elo · rank #179

Parameters

Undisclosed

Active params

—

Context

300K tokens

Architecture

Transformer, architecture/size undisclosed

License

Proprietary (AWS Bedrock service terms)

Languages

200+

API price (in/out)

$0.8 / $3.2

Modalities

text · vision · video

Benchmark results

Bar shows position within the tracked field; marker = field best

ARC-ChallengeReasoning94.8%#8

best: Llama 3.1 405B · 96.9%

BIG-Bench HardReasoning86.9%#10

best: ERNIE 4.5 300B-A47B · 94.3%

BFCL v3Agents68.4%#13

best: Hunyuan-A13B · 78.3%

ChartQAVision89.2%#7

best: MiniMax-VL-01 · 91.7%

DocVQAVision93.5%#14

best: Qwen2-VL-72B · 96.5%

DROPReasoning85.4#14

best: Hunyuan-T1 · 93.1

GPQA DiamondReasoning46.9%#198

best: GPT-5.6 · 94.6%

GSM8KMath94.8%#11

best: Llama 3.1 405B · 96.8%

HumanEvalCoding89.0%#22

best: Claude Opus 4.5 · 99.4%

IFEvalReasoning92.1%#9

best: Gemma 4 26B A4B · 98.5%

MATH-500Math76.6%#74

best: GPT-5 · 99.4%

MMLUKnowledge85.9%#48

best: OpenAI o3 · 92.9%

MMMUVision61.7%#76

best: Claude Fable 5 · 89.3%

MT-BenchHuman preference8.5#26

best: Hunyuan-Large (A52B) · 9.4

Run it locally

Closed weights — available via API only. No local deployment.

Input / M tok

$0.8

Output / M tok

$3.2

Amazon Nova family

Elo progression across releases

Amazon Nova LiteDec 20241039.0 Amazon Nova MicroDec 2024923.2 Amazon Nova ProDec 20241216.3 Amazon Nova PremierApr 20251235.4

Resources

DOCSdocs.aws.amazon.com/nova/latest/userguide/what-is-nova.html APIAvailable via Amazon API

API price $0.8/$3.2 · each benchmark row carries its own source badge (see methodology)