Model comparison
Amazon Nova Micro vs o3
o3 is the stronger model overall, scoring 47.4 to 29.9 on the Noometry Index. Amazon Nova Micro costs 57× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and o3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.5 to 29.2.
- The biggest single-benchmark swing is Omni-MATH: 21.4% for Amazon Nova Micro and 71.4% for o3.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $2 / $8 for o3.
- o3 accepts more context: 200K tokens versus 128K.
Side by side
| Amazon Nova Micro | o3 | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 29.9 | 47.4 |
| Released | 2024-12-03 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 200K |
| Max output | 10K | 100K |
| Input $ / M tokens | $0.035 | $2 |
| Output $ / M tokens | $0.14 | $8 |
| Results tracked | 32 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
Amazon Nova Micro: 30.0 (#289), o3: 47.3 (#57)
| Benchmark | Amazon Nova Micro | o3 |
|---|---|---|
| LMArena Coding | 1218 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| LiveBench Coding | 20.2% | — |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use o3 leads
Amazon Nova Micro: 21.9 (#125), o3: 34.3 (#42)
| Benchmark | Amazon Nova Micro | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
Amazon Nova Micro: 16.7 (#289), o3: 32.1 (#66)
| Benchmark | Amazon Nova Micro | o3 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1402 |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| LiveBench Reasoning | 25.1% | — |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 39.7% |
| Epoch Capabilities Index | — | 146.88 |
| ForecastBench | — | 62.5 |
| LiveBench | 29.6% | — |
Math o3 leads
Amazon Nova Micro: 24.9 (#252), o3: 48.9 (#49)
| Benchmark | Amazon Nova Micro | o3 |
|---|---|---|
| Omni-MATH | 21.4% | 71.4% |
| LMArena Math | 1206 | 1426 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| LiveBench Math | 34.5% | — |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
Amazon Nova Micro: 29.2 (#231), o3: 54.5 (#47)
| Benchmark | Amazon Nova Micro | o3 |
|---|---|---|
| MMLU-Pro | 51.1% | 85.9% |
| GPQA (HELM) | 38.3% | 75.3% |
| LMArena Expert | 1184 | 1403 |
| GPQA Diamond | — | 81.8% |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| Confabulations | — | 14.4% |
| Vectara Hallucination Rate | 5.5% | — |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, o3: 40.7 (#35)
| Benchmark | Amazon Nova Micro | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual o3 leads
Amazon Nova Micro: 36.7 (#234), o3: 51.9 (#99)
| Benchmark | Amazon Nova Micro | o3 |
|---|---|---|
| LMArena Non-English | 1186 | 1402 |
| LMArena Chinese | 1209 | 1438 |
| LMArena French | 1237 | 1430 |
| LMArena German | 1192 | 1420 |
| LMArena Japanese | 1154 | 1404 |
| LMArena Korean | 1150 | 1371 |
| LMArena Russian | 1185 | 1407 |
| LMArena Spanish | 1225 | 1395 |
Instruction Following o3 leads
Amazon Nova Micro: 56.6 (#267), o3: 73.0 (#122)
| Benchmark | Amazon Nova Micro | o3 |
|---|---|---|
| IFEval | 76% | 86.9% |
| LMArena Instruction Following | 1174 | 1368 |
| LiveBench Instruction Following | 48% | — |
Long Context o3 leads
Amazon Nova Micro: 36.5 (#224), o3: 53.2 (#6)
| Benchmark | Amazon Nova Micro | o3 |
|---|---|---|
| LMArena Longer Query | 1206 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
Amazon Nova Micro: 39.7 (#242), o3: 63.7 (#62)
| Benchmark | Amazon Nova Micro | o3 |
|---|---|---|
| LMArena Text | 1208 | 1410 |
| LMArena Creative Writing | 1172 | 1359 |
| WildBench | 74.3% | 86.1% |
| LMArena Multi-Turn | 1178 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than o3?
o3 is the stronger model overall, scoring 47.4 to 29.9 on the Noometry Index. Amazon Nova Micro costs 57× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or o3?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; o3 lists at $2 and $8.
Is Amazon Nova Micro or o3 better for coding?
o3 scores higher on coding benchmarks: 47.3 versus 30.0 in the Noometry coding category.
Which has the bigger context window?
o3 does, with 200K tokens against 128K.
How many benchmarks do Amazon Nova Micro and o3 share?
23 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and o3 has 63.