EBEasy BenchmarksLLM model index
Workspace
Overview
Benchmarks
Benchmarks list
Overall Index
Coding
Math
MMLU-Pro
Speed
Value
Models
All models
GPT-5.5 (xhigh)
GPT-5.5 (high)
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
Gemini 3.1 Pro Preview
GPT-5.4 (xhigh)
Artificial Analysis data
Back

Amazon

Nova 2.0 Lite (Non-reasoning)

Nova 2.0 Lite (Non-reasoning) is an Amazon Nova model profile, part of Amazon's Bedrock model family for enterprise generative AI, multimodal applications, and cost-scaled production workloads. The local snapshot shows how this exact Nova variant performs against other commercial models on benchmarks, speed, and pricing.

Amazon Nova models

Operational Metrics

Output Speed214.2 tok/s
First Token0.87s
Blended Price$0.850/M

Model Metadata

Queryable facts extracted from the upstream model payload.

ReleaseOct 29, 2025
Context Windown/a
Modalitiesn/a
API fields: release_date

Strength: Speed

Rank #17 across 293 models.

214.2 tok/s

Watch Area: HLE

Rank #467 across 474 models.

3.0%

Watch Area: SciCode

Rank #328 across 472 models.

24.0%

Watch Area: Coding

Rank #284 across 410 models.

12.5

Strength Profile

Percentile score by analysis domain.

* Cost is inverted: lower input, output, and blended prices rank higher.

Benchmark Percentiles

Higher bars mean stronger relative placement.

All Benchmarks

MetricDomainValueRank
Artificial Analysis Intelligence Indexoverall18.0#271
Artificial Analysis Coding Indexcoding12.5#284
Artificial Analysis Math Indexmath33.7#178
MMLU-Proreasoning74.3%#186
GPQA
reasoning
60.3%
#273
Humanity's Last Examreasoning3.0%#467
LiveCodeBenchcoding34.6%#201
SciCodecoding, reasoning24.0%#328
Output Speedspeed214.2 tok/s#17
Time to First Tokenspeed0.87s#107
Blended Pricecost$0.850/M#161
Input Pricecost$0.300/M#140
Output Pricecost$2.50/M#181
Value Indexcost, overall21.2#188