Amazon, proprietary
Amazon Nova Pro
Amazon Nova Pro by Amazon ranks 281st of 354 ranked models on the Noometry Index as of October 2026, with a score of 31.0. Its strongest category is multimodal, where it ranks 126th. API pricing starts at $0.80 per million input tokens and $3.20 per million output tokens, with a 300K-token context window.
Last verified
Specifications
- Noometry rank
- #281 of 354
- Index score
- 31.0
- Evidence
- Confirmed 38 results
- Provider
- Amazon
- Released
- December 3, 2024
- Weights
- Proprietary
- Reasoning
- No
- Context window
- 300K
- Max output
- 10K
- Input price
- $0.80 / M
- Output price
- $3.20 / M
- Blended price
- $1.40 / M
- Output speed
- Not measured
- Value
- #149 of 219
- Knowledge cutoff
- October 2024
- Input
- text, image, video, pdf
Category scores
Each category score combines every public result we have in that category.
- Coding 35.1
- Agentic & Tool Use 16.7
- Reasoning 20.0
- Math 28.5
- Knowledge 27.4
- Multimodal 25.0
- Multilingual 39.7
- Instruction Following 64.9
- Long Context 38.1
- Writing & Preference 43.9
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 35.1 | #229 | 2 |
| Agentic & Tool Use | 16.7 | #147 | 2 |
| Reasoning | 20.0 | #243 | 3 |
| Math | 28.5 | #243 | 3 |
| Knowledge | 27.4 | #250 | 6 |
| Multimodal | 25.0 | #126 | 1 |
| Multilingual | 39.7 | #223 | 1 |
| Instruction Following | 64.9 | #226 | 3 |
| Long Context | 38.1 | #205 | 1 |
| Writing & Preference | 43.9 | #226 | 6 |
Strengths and weaknesses
Categories where Amazon Nova Pro places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Coding | 35.1 | −3.6 | #229 of 340, top 68% |
| Long Context | 38.1 | −2.9 | #205 of 296, top 70% |
| Reasoning | 20.0 | −3.6 | #243 of 350, top 70% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Multimodal | 25.0 | −13.5 | #126 of 128, top 99% |
| Agentic & Tool Use | 16.7 | −13.7 | #147 of 154, top 96% |
| Knowledge | 27.4 | −9.9 | #250 of 314, top 80% |
Closest competitors
The models ranked just above and below Amazon Nova Pro. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Gemma 1.1 7b IT | #277 | 31.3 | — | — | Compare |
| Mistral Small 3 | #278 | 31.2 | $0.0575 | — | Compare |
| Phi-4 | #279 | 31.2 | $0.0875 | — | Compare |
| Mistral Small 3.2 | #280 | 31.2 | $0.13 | 68 | Compare |
| Llama 4 Maverick | #282 | 30.9 | $0.30 | 456 | Compare |
| Phi-4 Mini | #283 | 30.9 | $0.13 | — | Compare |
| Gemma 3 27B | #284 | 30.8 | $0.10 | 62 | Compare |
| Qwen1.5-72B | #285 | 30.8 | — | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Coding | 38.1% | #25 of 39, top 65% | Epoch AI | ||
| LMArena Coding | 1270 | #214 of 294, top 73% | LMArena | 2026-10-08 |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | #42 of 49, top 86% | fc | Berkeley Function Calling Leaderboard | |
| TheAgentCompany | 1.7% | #13 of 14, top 93% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Reasoning | 32.6% | #30 of 39, top 77% | Epoch AI | ||
| LMArena Hard Prompts | 1246 | #223 of 297, top 76% | LMArena | 2026-10-08 | |
| LiveBench Data Analysis | 48.3% | #27 of 39, top 70% | Epoch AI | ||
| Epoch Capabilities Index | 123.8 | #159 of 213, top 75% | Epoch AI | 2024-12-03 | |
| LiveBench | 43.5% | #27 of 39, top 70% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Omni-MATH | 24.2% | #46 of 57, top 81% | HELM Capabilities | ||
| LiveBench Math | 38% | #28 of 39, top 72% | Epoch AI | ||
| LMArena Math | 1252 | #211 of 285, top 75% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Humanity's Last Exam | 4.4% | #38 of 41, top 93% | Epoch AI | ||
| MMLU-Pro | 67.3% | #37 of 58, top 64% | HELM Capabilities | ||
| Confabulations (lower is better) | 30.1% | #47 of 51, top 93% | Lech Mazur benchmarks | ||
| Vectara Hallucination Rate (lower is better) | 5.1% | #8 of 96, top 9% | Vectara Hallucination Leaderboard | ||
| GPQA (HELM) | 44.6% | #36 of 57, top 64% | HELM Capabilities | ||
| LMArena Expert | 1211 | #217 of 273, top 80% | LMArena | 2026-10-08 | |
| MMLU | 82% | #12 of 81, top 15% | Epoch AI |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 980 | #120 of 122, top 99% | LMArena | 2026-10-09 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1234 | #223 of 297, top 76% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1244 | #210 of 285, top 74% | LMArena | 2026-10-08 | |
| LMArena French | 1271 | #176 of 223, top 79% | LMArena | 2026-10-08 | |
| LMArena German | 1243 | #180 of 231, top 78% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1200 | #161 of 211, top 77% | LMArena | 2026-10-08 | |
| LMArena Korean | 1203 | #160 of 213, top 76% | LMArena | 2026-10-08 | |
| LMArena Russian | 1240 | #218 of 283, top 78% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1182 | #198 of 226, top 88% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Instruction Following | 67.1% | #22 of 39, top 57% | Epoch AI | ||
| IFEval | 81.5% | #36 of 57, top 64% | HELM Capabilities | ||
| LMArena Instruction Following | 1235 | #225 of 298, top 76% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1255 | #218 of 291, top 75% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1259 | #223 of 297, top 76% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1212 | #226 of 295, top 77% | LMArena | 2026-10-08 | |
| Short-Story Creative Writing | 60.5% | #39 of 39, top 100% | Epoch AI | ||
| WildBench | 77.7% | #42 of 57, top 74% | HELM Capabilities | ||
| LMArena Multi-Turn | 1246 | #225 of 295, top 77% | LMArena | 2026-10-08 | |
| LiveBench Language | 37% | #21 of 39, top 54% | Epoch AI |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| bedrock | $0.80 | $3.20 | $0.20 | 2026-10-10 |
| openrouter | $0.80 | $3.20 | — | 2026-10-10 |
Compare Amazon Nova Pro
- Amazon Nova Pro vs Mistral Small 3.2
- Amazon Nova Pro vs Llama 4 Maverick
- Amazon Nova Pro vs Phi-4
- Amazon Nova Pro vs Phi-4 Mini
- Amazon Nova Pro vs Mistral Small 3
- Amazon Nova Pro vs Gemma 3 27B
- Amazon Nova Pro vs GPT-6 Astra
- Amazon Nova Pro vs Claude Fable 5.1
- Amazon Nova Pro vs Gemini 3.8 Flash
- Amazon Nova Pro vs Kimi K3
- Amazon Nova Pro vs Grok 4.6
- Amazon Nova Pro vs Qwen3.8 Max
- Amazon Nova Pro vs GLM-5.3
- Amazon Nova Pro vs Muse Spark 1.3
Frequently asked questions
How good is Amazon Nova Pro?
Amazon Nova Pro by Amazon ranks 281st of 354 ranked models on the Noometry Index as of October 2026, with a score of 31.0. Its strongest category is multimodal, where it ranks 126th. API pricing starts at $0.80 per million input tokens and $3.20 per million output tokens, with a 300K-token context window.
How much does Amazon Nova Pro cost?
Amazon Nova Pro costs $0.80 per million input tokens and $3.20 per million output tokens on bedrock, with cached input at $0.20.
What is Amazon Nova Pro's context window?
Amazon Nova Pro accepts up to 300K tokens of input and can write up to 10K tokens in one response.
Is Amazon Nova Pro open source?
No. Amazon Nova Pro is proprietary and available only through Amazon's API and partner platforms.
What are Amazon Nova Pro's strengths and weaknesses?
Relative to other ranked models, Amazon Nova Pro places best in coding, long context, reasoning and lowest in multimodal, agentic & tool use, knowledge.
What is Amazon Nova Pro best at?
Its best category is multimodal, where it ranks 126th on Noometry.