amazon.nova-pro-v1:0: benchmark scores, price and ranking

amazon.nova-pro-v1:0 from Amazon ranks #511 of 743 LLMs on the LLMs Tiger aggregate benchmark score (46.5), based on 2 benchmark results captured up to 2026-10-13.

Organisation: Amazon
Type: Frontier model
Open weights: No
Released: 2024-12-03 (source: epoch)
Context window: 300,000 tokens
Cheapest API price: $0.800 in / $3.20 out per million tokens (via bedrock, observed 2026-10-13T20:47Z)
Aggregate rank: #511 of 743 (score 46.5)

Across the 2 benchmarks where at least ten models are scored, amazon.nova-pro-v1:0 is in the top 10% on 0 and in the top half on 0.

Its cheapest listed input price, $0.800 per million tokens, is lower than that of 38% of the 427 models with a listed price.

amazon.nova-pro-v1:0 benchmark results

amazon.nova-pro-v1:0 benchmark scores, ranked against all models measured on each benchmark
Benchmark	Score	Rank	Source	Captured
Humanity's Last Exam	4.4%	#24 of 27	Epoch AI Benchmarking Hub	2026-10-13
TheAgentCompany	1.7%	#12 of 13	Epoch AI Benchmarking Hub	2026-10-13

About amazon.nova-pro-v1:0

amazon.nova-pro-v1:0 is a frontier model from Amazon. It was released on 2024-12-03, according to Epoch AI. It accepts up to 300,000 tokens of input at once. The cheapest API listing we track charges $0.800 per million input tokens and $3.20 per million output tokens, through bedrock. We hold 2 benchmark results for it across 2 areas, and none is in the top tenth of its board.

Where amazon.nova-pro-v1:0 stands

On our aggregate score, amazon.nova-pro-v1:0 is #511 of 743 ranked models, in the lower half. Its score is 46.5; the scale is centred on 50, so it sits 3.5 points below the typical model. That beats 31% of the ranked field. Among the 3 ranked Amazon models it is #1. The next one down is amazon.nova-lite-v1:0 at 45.7.

amazon.nova-pro-v1:0, benchmark by benchmark

Humanity's Last Exam is a weak spot. amazon.nova-pro-v1:0 scores 4.4%, #24 of 27, behind 85% of the models measured. The leader, Muse Spark, reaches 40.6%. It covers expert-level questions across domains. The board median is 10.7%, so amazon.nova-pro-v1:0 is 6.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

TheAgentCompany is a weak spot. amazon.nova-pro-v1:0 scores 1.7%, #12 of 13, behind 85% of the models measured. The leader, gemini-2.5-flash-preview-09-2025, reaches 41.1%. It covers work tasks in a simulated software company. The board median is 8.6%, so amazon.nova-pro-v1:0 is 6.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

amazon.nova-pro-v1:0 has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so amazon.nova-pro-v1:0 costs more than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on Claude Haiku 4.5 (Thinking 32K) ($1.00) and claude-haiku-4-5-20251001_32K ($1.00).

Release history

The Amazon model released before it was amazon.nova-lite-v1:0 on 2024-12-03, which scores 45.7.

Reading these numbers

The 2 scores on this page come from 1 source: Epoch AI Benchmarking Hub (2). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.

Models ranked nearby

#508 grok-3 (46.5)
#509 Mellum2-12B-A2.5B-Instruct-SFT (46.5)
#510 Qwen2.5-Coder-3B-Instruct (46.5)
#512 aya-expanse-32b (46.5)
#513 Mistral Small 4 (46.5)
#514 Qwen2-VL-7B-Instruct (46.5)