Model comparison
Amazon Nova Pro vs GPT-5 Nano
GPT-5 Nano is the stronger model overall, scoring 33.5 to 31.0 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Amazon Nova Pro scores higher in 4 categories and GPT-5 Nano in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-5 Nano leads 75.0 to 64.9.
- The biggest single-benchmark swing is Omni-MATH: 24.2% for Amazon Nova Pro and 54.6% for GPT-5 Nano.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- GPT-5 Nano accepts more context: 400K tokens versus 300K.
Side by side
| Amazon Nova Pro | GPT-5 Nano | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 33.5 |
| Released | 2024-12-03 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 400K |
| Max output | 10K | 128K |
| Input $ / M tokens | $0.80 | $0.05 |
| Output $ / M tokens | $3.20 | $0.40 |
| Results tracked | 38 | 49 |
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-5 Nano: 33.6 (#254)
| Benchmark | Amazon Nova Pro | GPT-5 Nano |
|---|---|---|
| LMArena Coding | 1270 | 1351 |
| SWE-bench Verified (bash only) | — | 34.8% |
| WeirdML | — | 38.1% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 718.67 |
Agentic & Tool Use GPT-5 Nano leads
Amazon Nova Pro: 16.7 (#147), GPT-5 Nano: 25.8 (#106)
| Benchmark | Amazon Nova Pro | GPT-5 Nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 51.5% |
| Terminal-Bench | — | 21.8% |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), GPT-5 Nano: 16.3 (#306)
| Benchmark | Amazon Nova Pro | GPT-5 Nano |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1328 |
| Epoch Capabilities Index | 123.8 | 139.38 |
| ARC-AGI-2 | — | 2.6% |
| Kagi LLM Benchmark | — | 62.2% |
| ARC-AGI-1 | — | 20.7% |
| Chess Puzzles | — | 27% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 62.7% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 7.9% |
| ForecastBench | — | 59.1 |
| LiveBench | 43.5% | — |
Math Too close to call
Amazon Nova Pro: 28.5 (#243), GPT-5 Nano: 29.4 (#241)
| Benchmark | Amazon Nova Pro | GPT-5 Nano |
|---|---|---|
| Omni-MATH | 24.2% | 54.6% |
| LMArena Math | 1252 | 1317 |
| FrontierMath (Tiers 1-3) | — | 20% |
| FrontierMath Tier 4 | — | 2.4% |
| OTIS Mock AIME 2024-2025 | — | 81.1% |
| ProofBench | — | 12% |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 95.2% |
| FrontierMath (Feb 2025 set) | — | 8.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5 Nano leads
Amazon Nova Pro: 27.4 (#250), GPT-5 Nano: 35.9 (#178)
| Benchmark | Amazon Nova Pro | GPT-5 Nano |
|---|---|---|
| MMLU-Pro | 67.3% | 77.8% |
| Vectara Hallucination Rate | 5.1% | 10.5% |
| GPQA (HELM) | 44.6% | 67.9% |
| LMArena Expert | 1211 | 1321 |
| GPQA Diamond | — | 69.4% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 11.7% |
| Confabulations | 30.1% | — |
| MMLU | 82% | — |
Multimodal GPT-5 Nano leads
Amazon Nova Pro: 25.0 (#126), GPT-5 Nano: 31.3 (#108)
| Benchmark | Amazon Nova Pro | GPT-5 Nano |
|---|---|---|
| LMArena Vision | 980 | 1159 |
| VPCT | — | 37.2% |
Multilingual GPT-5 Nano leads
Amazon Nova Pro: 39.7 (#223), GPT-5 Nano: 45.3 (#172)
| Benchmark | Amazon Nova Pro | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1234 | 1313 |
| LMArena Chinese | 1244 | 1356 |
| LMArena German | 1243 | 1327 |
| LMArena Japanese | 1200 | 1226 |
| LMArena Korean | 1203 | 1269 |
| LMArena Russian | 1240 | 1296 |
| LMArena Spanish | 1182 | 1360 |
| LMArena French | 1271 | — |
Instruction Following GPT-5 Nano leads
Amazon Nova Pro: 64.9 (#226), GPT-5 Nano: 75.0 (#79)
| Benchmark | Amazon Nova Pro | GPT-5 Nano |
|---|---|---|
| IFEval | 81.5% | 93.2% |
| LMArena Instruction Following | 1235 | 1306 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), GPT-5 Nano: 31.3 (#281)
| Benchmark | Amazon Nova Pro | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1255 | 1312 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), GPT-5 Nano: 39.1 (#249)
| Benchmark | Amazon Nova Pro | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1259 | 1320 |
| LMArena Creative Writing | 1212 | 1249 |
| WildBench | 77.7% | 80.6% |
| LMArena Multi-Turn | 1246 | 1311 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 705 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than GPT-5 Nano?
GPT-5 Nano is the stronger model overall, scoring 33.5 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or GPT-5 Nano?
GPT-5 Nano is cheaper. It lists at $0.05 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-5 Nano better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 300K.
How many benchmarks do Amazon Nova Pro and GPT-5 Nano share?
25 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-5 Nano has 49.