Model comparison
Amazon Nova Pro vs GPT-4.1 nano
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 27.9 on the Noometry Index. GPT-4.1 nano costs 8.0× less per token, which makes it the better buy when Amazon Nova Pro's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. Amazon Nova Pro scores higher in 6 categories and GPT-4.1 nano in 4 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where Amazon Nova Pro leads 38.1 to 23.7.
- The biggest single-benchmark swing is Omni-MATH: 24.2% for Amazon Nova Pro and 36.7% for GPT-4.1 nano.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 300K.
Side by side
| Amazon Nova Pro | GPT-4.1 nano | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 27.9 |
| Released | 2024-12-03 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 1.05M |
| Max output | 10K | 33K |
| Input $ / M tokens | $0.80 | $0.10 |
| Output $ / M tokens | $3.20 | $0.40 |
| Results tracked | 38 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Pro leads
Amazon Nova Pro: 35.1 (#229), GPT-4.1 nano: 24.1 (#330)
| Benchmark | Amazon Nova Pro | GPT-4.1 nano |
|---|---|---|
| LMArena Coding | 1270 | 1306 |
| Aider Polyglot | — | 8.9% |
| SciCode | — | 25.9% |
| WeirdML | — | 19% |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use GPT-4.1 nano leads
Amazon Nova Pro: 16.7 (#147), GPT-4.1 nano: 26.5 (#104)
| Benchmark | Amazon Nova Pro | GPT-4.1 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 33% |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), GPT-4.1 nano: 8.5 (#349)
| Benchmark | Amazon Nova Pro | GPT-4.1 nano |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1286 |
| Epoch Capabilities Index | 123.8 | 129.62 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 33.3% |
| ARC-AGI-1 | — | 0% |
| CritPt | — | 0% |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 52.5% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 5.5% |
| LiveBench | 43.5% | — |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), GPT-4.1 nano: 26.9 (#252)
| Benchmark | Amazon Nova Pro | GPT-4.1 nano |
|---|---|---|
| Omni-MATH | 24.2% | 36.7% |
| LMArena Math | 1252 | 1274 |
| OTIS Mock AIME 2024-2025 | — | 28.9% |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 70% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Amazon Nova Pro leads
Amazon Nova Pro: 27.4 (#250), GPT-4.1 nano: 21.8 (#273)
| Benchmark | Amazon Nova Pro | GPT-4.1 nano |
|---|---|---|
| MMLU-Pro | 67.3% | 55% |
| GPQA (HELM) | 44.6% | 50.7% |
| LMArena Expert | 1211 | 1272 |
| GPQA Diamond | — | 48.9% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 6% |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| MMLU | 82% | — |
Multimodal GPT-4.1 nano leads
Amazon Nova Pro: 25.0 (#126), GPT-4.1 nano: 29.2 (#113)
| Benchmark | Amazon Nova Pro | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | 980 | 1063 |
Multilingual GPT-4.1 nano leads
Amazon Nova Pro: 39.7 (#223), GPT-4.1 nano: 41.6 (#205)
| Benchmark | Amazon Nova Pro | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | 1234 | 1260 |
| LMArena Chinese | 1244 | 1270 |
| LMArena German | 1243 | 1288 |
| LMArena Japanese | 1200 | 1198 |
| LMArena Russian | 1240 | 1261 |
| LMArena French | 1271 | — |
| LMArena Korean | 1203 | — |
| LMArena Spanish | 1182 | — |
Instruction Following GPT-4.1 nano leads
Amazon Nova Pro: 64.9 (#226), GPT-4.1 nano: 67.8 (#193)
| Benchmark | Amazon Nova Pro | GPT-4.1 nano |
|---|---|---|
| IFEval | 81.5% | 84.3% |
| LMArena Instruction Following | 1235 | 1267 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), GPT-4.1 nano: 23.7 (#296)
| Benchmark | Amazon Nova Pro | GPT-4.1 nano |
|---|---|---|
| LMArena Longer Query | 1255 | 1283 |
| Fiction.LiveBench | — | 25% |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), GPT-4.1 nano: 40.5 (#243)
| Benchmark | Amazon Nova Pro | GPT-4.1 nano |
|---|---|---|
| LMArena Text | 1259 | 1285 |
| LMArena Creative Writing | 1212 | 1260 |
| WildBench | 77.7% | 81.2% |
| LMArena Multi-Turn | 1246 | 1277 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 946 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than GPT-4.1 nano?
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 27.9 on the Noometry Index. GPT-4.1 nano costs 8.0× less per token, which makes it the better buy when Amazon Nova Pro's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or GPT-4.1 nano?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or GPT-4.1 nano better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 300K.
How many benchmarks do Amazon Nova Pro and GPT-4.1 nano share?
22 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-4.1 nano has 38.