Amazon

Nova Lite — Benchmark Scores, Pricing & Performance Analysis

BUDGETAmazon
Chatbot Arena ELO
1110
Output Speed
150 tok/s
Input Cost
$0.06/1M
Output Cost
$0.24/1M
Context Window
300K
Max Output
5K
Knowledge Cutoff
Oct 2024
Accepts
text, image

Nova Lite by Amazon demonstrates fast output speed, competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

General Benchmarks

MMLU-Pro
45.0%66th of 66

Massive Multitask Language Understanding professional benchmark

HuggingFace Leaderboard
Chatbot Arena ELO
111074th of 74

Human preference ELO from blind head-to-head votes

LMSYS / HuggingFace

Coding Benchmarks

LiveCodeBench
14.0%66th of 66

Live competitive programming benchmark

livecodebench.github.io
HumanEval+
55.0%66th of 66

Code generation correctness with extended tests

Papers
SWE-bench Verified
10.0%67th of 67

Real-world software engineering task resolution

swebench.com

Math Benchmarks

GSM8K
68.0%66th of 66

Grade school math word problems

Papers
MATH
40.0%66th of 66

Competition mathematics problem solving

Papers

Reasoning Benchmarks

ARC-AGI
3.0%65th of 66

Abstraction and Reasoning Corpus for general intelligence

arcprize.org
GPQA Diamond
20.0%138th of 140

Graduate-level science Q&A by domain experts

Papers

Speed Benchmarks

Time to First Token
150 ms11th of 92

Latency before first token arrives

Aggregated
Output Speed
150 tok/s19th of 94

Tokens generated per second

Aggregated

Cost Benchmarks

Input Cost
$0.0696th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$0.24119th of 413

Cost per 1M output tokens

OpenRouter API

Context Benchmarks

Context Length
300K106th of 451

Maximum context window size

OpenRouter API

Available from 3 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 2 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Eden AI$0.06$0.24—300K—
Vercel AI Gateway$0.06$0.24$0.015300KSupported
Amazon Bedrock$0.064$0.256$0.016300KSupported

Nova Lite — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

Nova Lite — Frequently Asked Questions

How intelligent is Nova Lite?

Nova Lite scores 1110 on the Chatbot Arena ELO rating, making it an entry-level AI model. This score is based on blind head-to-head human preference voting.

How much does Nova Lite cost?

Nova Lite costs $0.06 per 1M input tokens and $0.24 per 1M output tokens. This makes it one of the more affordable models.

How fast is Nova Lite?

Nova Lite generates output at 150 tokens per second, which is very fast compared to other models. The time to first token is 150 ms.

How good is Nova Lite at coding?

Nova Lite achieves 10.0% on SWE-bench Verified, demonstrating basic real-world software engineering capability. This benchmark tests the model's ability to resolve actual GitHub issues.

How good is Nova Lite at math and reasoning?

Nova Lite scores 40.0% on the MATH benchmark (competition-level mathematics). It also achieves 20.0% on GPQA Diamond, a graduate-level science reasoning benchmark.

What is the context window of Nova Lite?

Nova Lite has a context window of 300K tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Nova Lite?

Nova Lite was created by Amazon. It is classified as a budget model in our catalogue.

Is Nova Lite open source?

No, Nova Lite is a proprietary model. It is available through Amazon's API and compatible providers.