Model comparison
Amazon Nova Pro vs GPT-5.4 nano
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 31.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and GPT-5.4 nano in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 nano leads 41.9 to 27.4.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- GPT-5.4 nano accepts more context: 400K tokens versus 300K.
Side by side
| Amazon Nova Pro | GPT-5.4 nano | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 41.9 |
| Released | 2024-12-03 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 400K |
| Max output | 10K | 128K |
| Input $ / M tokens | $0.80 | $0.20 |
| Output $ / M tokens | $3.20 | $1.25 |
| Results tracked | 38 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
Amazon Nova Pro: 35.1 (#229), GPT-5.4 nano: 43.6 (#84)
| Benchmark | Amazon Nova Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Coding | 1270 | 1405 |
| SciCode | — | 46.9% |
| WeirdML | — | 49.2% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 1,005 |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), GPT-5.4 nano: —
| Benchmark | Amazon Nova Pro | GPT-5.4 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning GPT-5.4 nano leads
Amazon Nova Pro: 20.0 (#243), GPT-5.4 nano: 23.7 (#173)
| Benchmark | Amazon Nova Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1381 |
| Epoch Capabilities Index | 123.8 | 145.81 |
| ARC-AGI-2 | — | 5.7% |
| Kagi LLM Benchmark | — | 39.7% |
| ARC-AGI-1 | — | 51.5% |
| CritPt | — | 9.3% |
| Chess Puzzles | — | 30% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 36.9% |
| ForecastBench | — | 57.3 |
| LiveBench | 43.5% | — |
Math GPT-5.4 nano leads
Amazon Nova Pro: 28.5 (#243), GPT-5.4 nano: 40.9 (#88)
| Benchmark | Amazon Nova Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Math | 1252 | 1406 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 87.8% |
| ProofBench | — | 5% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| FrontierMath (Feb 2025 set) | — | 25.9% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GPT-5.4 nano leads
Amazon Nova Pro: 27.4 (#250), GPT-5.4 nano: 41.9 (#103)
| Benchmark | Amazon Nova Pro | GPT-5.4 nano |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 3.1% |
| LMArena Expert | 1211 | 1396 |
| GPQA Diamond | — | 78.5% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 11.7% |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal GPT-5.4 nano leads
Amazon Nova Pro: 25.0 (#126), GPT-5.4 nano: 36.7 (#78)
| Benchmark | Amazon Nova Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | 980 | 1196 |
Multilingual GPT-5.4 nano leads
Amazon Nova Pro: 39.7 (#223), GPT-5.4 nano: 48.6 (#140)
| Benchmark | Amazon Nova Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1234 | 1359 |
| LMArena Chinese | 1244 | 1392 |
| LMArena French | 1271 | 1396 |
| LMArena German | 1243 | 1367 |
| LMArena Japanese | 1200 | 1343 |
| LMArena Korean | 1203 | 1320 |
| LMArena Russian | 1240 | 1363 |
| LMArena Spanish | 1182 | 1371 |
Instruction Following GPT-5.4 nano leads
Amazon Nova Pro: 64.9 (#226), GPT-5.4 nano: 71.9 (#144)
| Benchmark | Amazon Nova Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1235 | 1362 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context GPT-5.4 nano leads
Amazon Nova Pro: 38.1 (#205), GPT-5.4 nano: 41.6 (#137)
| Benchmark | Amazon Nova Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1255 | 1366 |
Writing & Preference GPT-5.4 nano leads
Amazon Nova Pro: 43.9 (#226), GPT-5.4 nano: 55.7 (#142)
| Benchmark | Amazon Nova Pro | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1259 | 1372 |
| LMArena Creative Writing | 1212 | 1314 |
| LMArena Multi-Turn | 1246 | 1382 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than GPT-5.4 nano?
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or GPT-5.4 nano?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or GPT-5.4 nano better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 nano does, with 400K tokens against 300K.
How many benchmarks do Amazon Nova Pro and GPT-5.4 nano share?
20 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-5.4 nano has 40.