Skip to main content

Nova Pro

AmazonEstablishedReleased Apr 1, 2025
Overall Score
Est. 10Prov. #117 of 119
Arena Elo
1059
Categories Ranked
8of 8
Price (1M tokens)
$ in / $ out
Speed
141tok/s
Context
128K
ProprietaryNon-Reasoning
Confidence
base

According to BenchLM.ai, Nova Pro ranks #117 out of 119 models on the provisional leaderboard with an overall score of 10/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Nova Pro is a proprietary model with a 128K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

This profile currently has 17 of 225 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Mathematics (#80), while its weakest is Multimodal & Grounded (#100). This performance profile makes it particularly strong for mathematical reasoning, scientific computing, and quantitative analysis.

Ranking Distribution

Category rank across 7 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

#99
4.8/ 100
Weight: 22%4 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

#88
9.0/ 100
Weight: 20%3 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

#84
17.9/ 100
Weight: 17%2 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

#99
10.4/ 100
Weight: 12%6 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

#80
9.7/ 100
Weight: 5%0 benchmarks
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

#85
8.8/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

#100
5.5/ 100
Weight: 12%1 benchmark
MMMU-ProOfficeQA ProCharXivCharXiv w/o tools

Inst. Following

#120
0.0/ 100
Weight: 5%1 benchmark
IFEvalIFBench

Chatbot Arena Performance

Text Overall1059

Benchmark Details

Only benchmark rows with an attached exact-source record are shown here. Source-unverified manual rows and generated rows are hidden from model pages.

Frequently Asked Questions

How does Nova Pro perform overall in AI benchmarks?

Nova Pro currently ranks #117 out of 119 models on BenchLM's provisional leaderboard with an overall score of 10 (estimated). It is created by Amazon and features a 128K context window.

Is Nova Pro good for knowledge and understanding?

Nova Pro ranks #99 out of 119 models in knowledge and understanding benchmarks with an average score of 10.4. There are stronger options in this category.

Is Nova Pro good for coding and programming?

Nova Pro ranks #88 out of 119 models in coding and programming benchmarks with an average score of 9. There are stronger options in this category.

Is Nova Pro good for reasoning and logic?

Nova Pro ranks #84 out of 119 models in reasoning and logic benchmarks with an average score of 17.9. There are stronger options in this category.

Is Nova Pro good for agentic tool use and computer tasks?

Nova Pro ranks #99 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 4.8. There are stronger options in this category.

Is Nova Pro good for multimodal and grounded tasks?

Nova Pro ranks #100 out of 119 models in multimodal and grounded tasks benchmarks with an average score of 5.5. There are stronger options in this category.

Is Nova Pro good for instruction following?

Nova Pro ranks #120 out of 119 models in instruction following benchmarks with an average score of 0. There are stronger options in this category.

Does Nova Pro have full benchmark coverage on BenchLM?

Not yet. Nova Pro currently has 17 published benchmark scores out of the 225 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Nova Pro?

Nova Pro has a context window of 128K, which determines how much text it can process in a single interaction.

Last updated: June 2, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Don't miss the next GPT moment

Which models moved up, what’s new, and what it costs. One email a week, 3-min read.

Free. One email per week.