Model comparison
Amazon Nova Micro vs GPT-5 Mini
GPT-5 Mini is the stronger model overall, scoring 41.8 to 30.4 on the Noometry Index. Amazon Nova Micro costs 11× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and GPT-5 Mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-5 Mini leads 76.2 to 56.3.
- The biggest single-benchmark swing is Omni-MATH: 21.4% for Amazon Nova Micro and 72.2% for GPT-5 Mini.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- GPT-5 Mini accepts more context: 400K tokens versus 128K.
Side by side
| Amazon Nova Micro | GPT-5 Mini | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 30.4 | 41.8 |
| Released | 2024-12-03 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 400K |
| Max output | 10K | 128K |
| Input $ / M tokens | $0.035 | $0.25 |
| Output $ / M tokens | $0.14 | $2 |
| Results tracked | 32 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
Amazon Nova Micro: 30.5 (#295), GPT-5 Mini: 40.1 (#146)
| Benchmark | Amazon Nova Micro | GPT-5 Mini |
|---|---|---|
| LMArena Coding | 1218 | 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 | 20.2% | — |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |
Agentic & Tool Use GPT-5 Mini leads
Amazon Nova Micro: 22.1 (#132), GPT-5 Mini: 31.1 (#70)
| Benchmark | Amazon Nova Micro | GPT-5 Mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | 55.5% |
| Terminal-Bench | — | 34.8% |
| Vending-Bench 2 | — | -31.18 |
Reasoning GPT-5 Mini leads
Amazon Nova Micro: 17.4 (#294), GPT-5 Mini: 23.9 (#168)
| Benchmark | Amazon Nova Micro | GPT-5 Mini |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1380 |
| 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 | 25.1% | — |
| Mystery Game Puzzles | — | 10% |
| DTBench | — | 80.5% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 34.2% |
| Epoch Capabilities Index | — | 145.52 |
| ForecastBench | — | 61 |
| LiveBench | 29.6% | — |
Math GPT-5 Mini leads
Amazon Nova Micro: 26.9 (#254), GPT-5 Mini: 46.7 (#69)
| Benchmark | Amazon Nova Micro | GPT-5 Mini |
|---|---|---|
| Omni-MATH | 21.4% | 72.2% |
| LMArena Math | 1206 | 1378 |
| FrontierMath (Tiers 1-3) | — | 46.7% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 9% |
| LiveBench Math | 34.5% | — |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 27.2% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GPT-5 Mini leads
Amazon Nova Micro: 29.6 (#237), GPT-5 Mini: 45.6 (#86)
| Benchmark | Amazon Nova Micro | GPT-5 Mini |
|---|---|---|
| MMLU-Pro | 51.1% | 83.5% |
| Vectara Hallucination Rate | 5.5% | 12.9% |
| GPQA (HELM) | 38.3% | 75.6% |
| LMArena Expert | 1184 | 1379 |
| GPQA Diamond | — | 75% |
| Humanity's Last Exam | — | 19.4% |
| SimpleQA Verified | — | 21.6% |
| Confabulations | — | 13.3% |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, GPT-5 Mini: 35.6 (#85)
| Benchmark | Amazon Nova Micro | GPT-5 Mini |
|---|---|---|
| LMArena Vision | — | 1202 |
| VPCT | — | 40.2% |
Multilingual GPT-5 Mini leads
Amazon Nova Micro: 36.5 (#239), GPT-5 Mini: 48.9 (#137)
| Benchmark | Amazon Nova Micro | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1186 | 1363 |
| LMArena Chinese | 1209 | 1385 |
| LMArena French | 1238 | 1386 |
| LMArena German | 1192 | 1366 |
| LMArena Japanese | 1154 | 1341 |
| LMArena Korean | 1150 | 1308 |
| LMArena Russian | 1185 | 1362 |
| LMArena Spanish | 1225 | 1355 |
Instruction Following GPT-5 Mini leads
Amazon Nova Micro: 56.3 (#272), GPT-5 Mini: 76.2 (#46)
| Benchmark | Amazon Nova Micro | GPT-5 Mini |
|---|---|---|
| IFEval | 76% | 92.7% |
| LMArena Instruction Following | 1174 | 1357 |
| LiveBench Instruction Following | 48% | — |
Long Context GPT-5 Mini leads
Amazon Nova Micro: 36.5 (#229), GPT-5 Mini: 41.9 (#132)
| Benchmark | Amazon Nova Micro | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1205 | 1355 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference GPT-5 Mini leads
Amazon Nova Micro: 39.5 (#247), GPT-5 Mini: 55.2 (#148)
| Benchmark | Amazon Nova Micro | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1208 | 1373 |
| LMArena Creative Writing | 1172 | 1325 |
| WildBench | 74.3% | 85.5% |
| LMArena Multi-Turn | 1178 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| EQ-Bench Creative Writing | — | 1313 |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than GPT-5 Mini?
GPT-5 Mini is the stronger model overall, scoring 41.8 to 30.4 on the Noometry Index. Amazon Nova Micro costs 11× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or GPT-5 Mini?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; GPT-5 Mini lists at $0.25 and $2.
Is Amazon Nova Micro or GPT-5 Mini better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Mini does, with 400K tokens against 128K.
How many benchmarks do Amazon Nova Micro and GPT-5 Mini share?
24 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and GPT-5 Mini has 60.