Model comparison
Amazon Nova Micro vs o1
o1 is the stronger model overall, scoring 40.6 to 29.9 on the Noometry Index. Amazon Nova Micro costs 429× less per token, which makes it the better buy when o1'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 o1 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where o1 leads 75.0 to 56.6.
- The biggest single-benchmark swing is LiveBench Reasoning: 25.1% for Amazon Nova Micro and 91.6% for o1.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $15 / $60 for o1.
- o1 accepts more context: 200K tokens versus 128K.
Side by side
| Amazon Nova Micro | o1 | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 29.9 | 40.6 |
| Released | 2024-12-03 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 200K |
| Max output | 10K | 100K |
| Input $ / M tokens | $0.035 | $15 |
| Output $ / M tokens | $0.14 | $60 |
| Results tracked | 32 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
Amazon Nova Micro: 30.0 (#289), o1: 45.7 (#64)
| Benchmark | Amazon Nova Micro | o1 |
|---|---|---|
| LiveBench Coding | 20.2% | 69.7% |
| LMArena Coding | 1218 | 1367 |
| Aider Polyglot | — | 61.7% |
| WeirdML | — | 47.6% |
| CadEval | — | 56% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |
Agentic & Tool Use o1 leads
Amazon Nova Micro: 21.9 (#125), o1: 24.3 (#111)
| Benchmark | Amazon Nova Micro | o1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |
Reasoning o1 leads
Amazon Nova Micro: 16.7 (#289), o1: 27.5 (#103)
| Benchmark | Amazon Nova Micro | o1 |
|---|---|---|
| LiveBench Reasoning | 25.1% | 91.6% |
| LMArena Hard Prompts | 1191 | 1372 |
| LiveBench Data Analysis | 34% | 65.5% |
| LiveBench | 29.6% | 75.7% |
| SimpleBench | — | 41.7% |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| DTBench | — | 74.7% |
| LMCA | — | 22.3% |
| Epoch Capabilities Index | — | 141.92 |
Math o1 leads
Amazon Nova Micro: 24.9 (#252), o1: 34.9 (#150)
| Benchmark | Amazon Nova Micro | o1 |
|---|---|---|
| LiveBench Math | 34.5% | 80.3% |
| LMArena Math | 1206 | 1388 |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| Omni-MATH | 21.4% | — |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |
Knowledge o1 leads
Amazon Nova Micro: 29.2 (#231), o1: 41.5 (#101)
| Benchmark | Amazon Nova Micro | o1 |
|---|---|---|
| LMArena Expert | 1184 | 1362 |
| GPQA Diamond | — | 76.8% |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| MMLU-Pro | 51.1% | — |
| Confabulations | — | 11.7% |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, o1: 33.6 (#87)
| Benchmark | Amazon Nova Micro | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |
Multilingual o1 leads
Amazon Nova Micro: 36.7 (#234), o1: 48.8 (#137)
| Benchmark | Amazon Nova Micro | o1 |
|---|---|---|
| LMArena Non-English | 1186 | 1359 |
| LMArena Chinese | 1209 | 1394 |
| LMArena French | 1237 | 1343 |
| LMArena German | 1192 | 1337 |
| LMArena Japanese | 1154 | 1346 |
| LMArena Korean | 1150 | 1396 |
| LMArena Russian | 1185 | 1356 |
| LMArena Spanish | 1225 | 1345 |
Instruction Following o1 leads
Amazon Nova Micro: 56.6 (#267), o1: 75.0 (#82)
| Benchmark | Amazon Nova Micro | o1 |
|---|---|---|
| LiveBench Instruction Following | 48% | 81.5% |
| LMArena Instruction Following | 1174 | 1368 |
| IFEval | 76% | — |
Long Context o1 leads
Amazon Nova Micro: 36.5 (#224), o1: 50.3 (#9)
| Benchmark | Amazon Nova Micro | o1 |
|---|---|---|
| LMArena Longer Query | 1206 | 1378 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference o1 leads
Amazon Nova Micro: 39.7 (#242), o1: 55.8 (#139)
| Benchmark | Amazon Nova Micro | o1 |
|---|---|---|
| LMArena Text | 1208 | 1366 |
| LMArena Creative Writing | 1172 | 1347 |
| LMArena Multi-Turn | 1178 | 1368 |
| LiveBench Language | 15.8% | 65.4% |
| Short-Story Creative Writing | — | 70.2% |
| WildBench | 74.3% | — |
Frequently asked questions
Is Amazon Nova Micro better than o1?
o1 is the stronger model overall, scoring 40.6 to 29.9 on the Noometry Index. Amazon Nova Micro costs 429× less per token, which makes it the better buy when o1's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or o1?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; o1 lists at $15 and $60.
Is Amazon Nova Micro or o1 better for coding?
o1 scores higher on coding benchmarks: 45.7 versus 30.0 in the Noometry coding category.
Which has the bigger context window?
o1 does, with 200K tokens against 128K.
How many benchmarks do Amazon Nova Micro and o1 share?
24 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and o1 has 52.