Model comparison
Amazon Nova Micro vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 30.4 on the Noometry Index. Amazon Nova Micro costs 31× less per token, which makes it the better buy when o4-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 o4-mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where o4-mini leads 75.2 to 56.3.
- The biggest single-benchmark swing is Omni-MATH: 21.4% for Amazon Nova Micro and 72% for o4-mini.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- o4-mini accepts more context: 200K tokens versus 128K.
Side by side
| Amazon Nova Micro | o4-mini | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 30.4 | 41.6 |
| Released | 2024-12-03 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 200K |
| Max output | 10K | 100K |
| Input $ / M tokens | $0.035 | $1.10 |
| Output $ / M tokens | $0.14 | $4.40 |
| Results tracked | 32 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Amazon Nova Micro: 30.5 (#295), o4-mini: 40.9 (#127)
| Benchmark | Amazon Nova Micro | o4-mini |
|---|---|---|
| LMArena Coding | 1218 | 1368 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| LiveBench Coding | 20.2% | — |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use o4-mini leads
Amazon Nova Micro: 22.1 (#132), o4-mini: 32.6 (#61)
| Benchmark | Amazon Nova Micro | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Amazon Nova Micro: 17.4 (#294), o4-mini: 24.6 (#162)
| Benchmark | Amazon Nova Micro | o4-mini |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1351 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| LiveBench Reasoning | 25.1% | — |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 77.6% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 26.5% |
| Epoch Capabilities Index | — | 145.64 |
| ForecastBench | — | 61.8 |
| LiveBench | 29.6% | — |
Math o4-mini leads
Amazon Nova Micro: 26.9 (#254), o4-mini: 40.8 (#89)
| Benchmark | Amazon Nova Micro | o4-mini |
|---|---|---|
| Omni-MATH | 21.4% | 72% |
| LMArena Math | 1206 | 1389 |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 81.7% |
| LiveBench Math | 34.5% | — |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Amazon Nova Micro: 29.6 (#237), o4-mini: 43.6 (#91)
| Benchmark | Amazon Nova Micro | o4-mini |
|---|---|---|
| MMLU-Pro | 51.1% | 82% |
| Vectara Hallucination Rate | 5.5% | 18.6% |
| GPQA (HELM) | 38.3% | 73.5% |
| LMArena Expert | 1184 | 1343 |
| GPQA Diamond | — | 79.6% |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| Confabulations | — | 15.8% |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, o4-mini: 40.2 (#49)
| Benchmark | Amazon Nova Micro | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual o4-mini leads
Amazon Nova Micro: 36.5 (#239), o4-mini: 47.0 (#154)
| Benchmark | Amazon Nova Micro | o4-mini |
|---|---|---|
| LMArena Non-English | 1186 | 1337 |
| LMArena Chinese | 1209 | 1354 |
| LMArena French | 1238 | 1364 |
| LMArena German | 1192 | 1336 |
| LMArena Japanese | 1154 | 1308 |
| LMArena Korean | 1150 | 1312 |
| LMArena Russian | 1185 | 1334 |
| LMArena Spanish | 1225 | 1347 |
Instruction Following o4-mini leads
Amazon Nova Micro: 56.3 (#272), o4-mini: 75.2 (#68)
| Benchmark | Amazon Nova Micro | o4-mini |
|---|---|---|
| IFEval | 76% | 92.8% |
| LMArena Instruction Following | 1174 | 1321 |
| LiveBench Instruction Following | 48% | — |
Long Context o4-mini leads
Amazon Nova Micro: 36.5 (#229), o4-mini: 45.5 (#33)
| Benchmark | Amazon Nova Micro | o4-mini |
|---|---|---|
| LMArena Longer Query | 1205 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference o4-mini leads
Amazon Nova Micro: 39.5 (#247), o4-mini: 54.0 (#152)
| Benchmark | Amazon Nova Micro | o4-mini |
|---|---|---|
| LMArena Text | 1208 | 1353 |
| LMArena Creative Writing | 1172 | 1294 |
| WildBench | 74.3% | 85.4% |
| LMArena Multi-Turn | 1178 | 1350 |
| Short-Story Creative Writing | — | 75% |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 30.4 on the Noometry Index. Amazon Nova Micro costs 31× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or o4-mini?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is Amazon Nova Micro or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
o4-mini does, with 200K tokens against 128K.
How many benchmarks do Amazon Nova Micro and o4-mini share?
24 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and o4-mini has 60.