Model comparison
Amazon Nova Pro vs GPT-5 Mini
GPT-5 Mini is the stronger model overall, scoring 41.8 to 31.0 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and GPT-5 Mini in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Mini leads 45.6 to 27.4.
- The biggest single-benchmark swing is Omni-MATH: 24.2% for Amazon Nova Pro and 72.2% for GPT-5 Mini.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- GPT-5 Mini accepts more context: 400K tokens versus 300K.
Side by side
| Amazon Nova Pro | GPT-5 Mini | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 41.8 |
| Released | 2024-12-03 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 400K |
| Max output | 10K | 128K |
| Input $ / M tokens | $0.80 | $0.25 |
| Output $ / M tokens | $3.20 | $2 |
| Results tracked | 38 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
Amazon Nova Pro: 35.1 (#229), GPT-5 Mini: 40.1 (#146)
| Benchmark | Amazon Nova Pro | GPT-5 Mini |
|---|---|---|
| LMArena Coding | 1270 | 1406 |
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| SWE-bench Multilingual | — | 39.7% |
| SciCode | — | 39.2% |
| WeirdML | — | 52.7% |
| LiveBench Coding | 38.1% | — |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |
Agentic & Tool Use GPT-5 Mini leads
Amazon Nova Pro: 16.7 (#147), GPT-5 Mini: 31.1 (#70)
| Benchmark | Amazon Nova Pro | GPT-5 Mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 55.5% |
| Terminal-Bench | — | 34.8% |
| TheAgentCompany | 1.7% | — |
| Vending-Bench 2 | — | -31.18 |
Reasoning GPT-5 Mini leads
Amazon Nova Pro: 20.0 (#243), GPT-5 Mini: 23.9 (#168)
| Benchmark | Amazon Nova Pro | GPT-5 Mini |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1380 |
| Epoch Capabilities Index | 123.8 | 145.52 |
| ARC-AGI-2 | — | 4.4% |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 54.3% |
| CritPt | — | 0% |
| Chess Puzzles | — | 30% |
| EnigmaEval | — | 8.2% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 10% |
| DTBench | — | 80.5% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 34.2% |
| ForecastBench | — | 61 |
| LiveBench | 43.5% | — |
Math GPT-5 Mini leads
Amazon Nova Pro: 28.5 (#243), GPT-5 Mini: 46.7 (#69)
| Benchmark | Amazon Nova Pro | GPT-5 Mini |
|---|---|---|
| Omni-MATH | 24.2% | 72.2% |
| LMArena Math | 1252 | 1378 |
| FrontierMath (Tiers 1-3) | — | 46.7% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 9% |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 27.2% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GPT-5 Mini leads
Amazon Nova Pro: 27.4 (#250), GPT-5 Mini: 45.6 (#86)
| Benchmark | Amazon Nova Pro | GPT-5 Mini |
|---|---|---|
| Humanity's Last Exam | 4.4% | 19.4% |
| MMLU-Pro | 67.3% | 83.5% |
| Confabulations | 30.1% | 13.3% |
| Vectara Hallucination Rate | 5.1% | 12.9% |
| GPQA (HELM) | 44.6% | 75.6% |
| LMArena Expert | 1211 | 1379 |
| GPQA Diamond | — | 75% |
| SimpleQA Verified | — | 21.6% |
| MMLU | 82% | — |
Multimodal GPT-5 Mini leads
Amazon Nova Pro: 25.0 (#126), GPT-5 Mini: 35.6 (#85)
| Benchmark | Amazon Nova Pro | GPT-5 Mini |
|---|---|---|
| LMArena Vision | 980 | 1202 |
| VPCT | — | 40.2% |
Multilingual GPT-5 Mini leads
Amazon Nova Pro: 39.7 (#223), GPT-5 Mini: 48.9 (#137)
| Benchmark | Amazon Nova Pro | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1234 | 1363 |
| LMArena Chinese | 1244 | 1385 |
| LMArena French | 1271 | 1386 |
| LMArena German | 1243 | 1366 |
| LMArena Japanese | 1200 | 1341 |
| LMArena Korean | 1203 | 1308 |
| LMArena Russian | 1240 | 1362 |
| LMArena Spanish | 1182 | 1355 |
Instruction Following GPT-5 Mini leads
Amazon Nova Pro: 64.9 (#226), GPT-5 Mini: 76.2 (#46)
| Benchmark | Amazon Nova Pro | GPT-5 Mini |
|---|---|---|
| IFEval | 81.5% | 92.7% |
| LMArena Instruction Following | 1235 | 1357 |
| LiveBench Instruction Following | 67.1% | — |
Long Context GPT-5 Mini leads
Amazon Nova Pro: 38.1 (#205), GPT-5 Mini: 41.9 (#132)
| Benchmark | Amazon Nova Pro | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1255 | 1355 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference GPT-5 Mini leads
Amazon Nova Pro: 43.9 (#226), GPT-5 Mini: 55.2 (#148)
| Benchmark | Amazon Nova Pro | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1259 | 1373 |
| LMArena Creative Writing | 1212 | 1325 |
| Short-Story Creative Writing | 60.5% | 83.1% |
| WildBench | 77.7% | 85.5% |
| LMArena Multi-Turn | 1246 | 1363 |
| EQ-Bench Creative Writing | — | 1313 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than GPT-5 Mini?
GPT-5 Mini is the stronger model overall, scoring 41.8 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or GPT-5 Mini?
GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or GPT-5 Mini better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Mini does, with 400K tokens against 300K.
How many benchmarks do Amazon Nova Pro and GPT-5 Mini share?
29 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-5 Mini has 60.