Model comparison
Amazon Nova Micro vs Claude Sonnet 4
Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 29.9 on the Noometry Index. Amazon Nova Micro costs 98× less per token, which makes it the better buy when Claude Sonnet 4'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 1 category and Claude Sonnet 4 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4 leads 57.3 to 39.7.
- The biggest single-benchmark swing is Omni-MATH: 21.4% for Amazon Nova Micro and 60.2% for Claude Sonnet 4.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Claude Sonnet 4 accepts more context: 200K tokens versus 128K.
Side by side
| Amazon Nova Micro | Claude Sonnet 4 | |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 29.9 | 40.6 |
| Released | 2024-12-03 | 2025-05-22 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 200K |
| Max output | 10K | 64K |
| Input $ / M tokens | $0.035 | $3 |
| Output $ / M tokens | $0.14 | $15 |
| Results tracked | 32 | 58 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Amazon Nova Micro: 30.0 (#289), Claude Sonnet 4: 44.0 (#70)
| Benchmark | Amazon Nova Micro | Claude Sonnet 4 |
|---|---|---|
| LMArena Coding | 1218 | 1414 |
| SWE-bench Verified (bash only) | — | 64.9% |
| Aider Polyglot | — | 61.3% |
| SciCode | — | 40% |
| GSO | — | 4.9% |
| WeirdML | — | 46.1% |
| LiveBench Coding | 20.2% | — |
| ALE-Bench | — | 655.35 |
Agentic & Tool Use Claude Sonnet 4 leads
Amazon Nova Micro: 21.9 (#125), Claude Sonnet 4: 38.3 (#29)
| Benchmark | Amazon Nova Micro | Claude Sonnet 4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
| TheAgentCompany | — | 33.1% |
| Cybench | — | 35% |
| DeepResearch Bench | — | 46.6% |
| OSWorld | — | 43.9% |
| METR Time Horizons | — | 62% |
Reasoning Claude Sonnet 4 leads
Amazon Nova Micro: 16.7 (#289), Claude Sonnet 4: 23.0 (#169)
| Benchmark | Amazon Nova Micro | Claude Sonnet 4 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1372 |
| ARC-AGI-2 | — | 5.9% |
| SimpleBench | — | 45.5% |
| Kagi LLM Benchmark | — | 73% |
| ARC-AGI-1 | — | 40% |
| CritPt | — | 0.3% |
| EnigmaEval | — | 3.1% |
| LiveBench Reasoning | 25.1% | — |
| DTBench | — | 77.1% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 29% |
| Epoch Capabilities Index | — | 141.69 |
| ForecastBench | — | 60.2 |
| LiveBench | 29.6% | — |
Math Claude Sonnet 4 leads
Amazon Nova Micro: 24.9 (#252), Claude Sonnet 4: 41.5 (#71)
| Benchmark | Amazon Nova Micro | Claude Sonnet 4 |
|---|---|---|
| Omni-MATH | 21.4% | 60.2% |
| LMArena Math | 1206 | 1375 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| LiveBench Math | 34.5% | — |
| MATH Level 5 | — | 84.4% |
| FrontierMath (Feb 2025 set) | — | 4.1% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Claude Sonnet 4 leads
Amazon Nova Micro: 29.2 (#231), Claude Sonnet 4: 41.6 (#99)
| Benchmark | Amazon Nova Micro | Claude Sonnet 4 |
|---|---|---|
| MMLU-Pro | 51.1% | 84.3% |
| Vectara Hallucination Rate | 5.5% | 10.3% |
| GPQA (HELM) | 38.3% | 70.6% |
| LMArena Expert | 1184 | 1371 |
| GPQA Diamond | — | 79.2% |
| Humanity's Last Exam | — | 7.8% |
| Confabulations | — | 13.2% |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, Claude Sonnet 4: 25.6 (#116)
| Benchmark | Amazon Nova Micro | Claude Sonnet 4 |
|---|---|---|
| LMArena Vision | — | 1191 |
| GeoBench | — | 37% |
| VPCT | — | 34% |
| MindCube | — | 44.8% |
Multilingual Claude Sonnet 4 leads
Amazon Nova Micro: 36.7 (#234), Claude Sonnet 4: 46.9 (#151)
| Benchmark | Amazon Nova Micro | Claude Sonnet 4 |
|---|---|---|
| LMArena Non-English | 1186 | 1333 |
| LMArena Chinese | 1209 | 1351 |
| LMArena French | 1237 | 1364 |
| LMArena German | 1192 | 1331 |
| LMArena Japanese | 1154 | 1301 |
| LMArena Korean | 1150 | 1293 |
| LMArena Russian | 1185 | 1355 |
| LMArena Spanish | 1225 | 1356 |
Instruction Following Claude Sonnet 4 leads
Amazon Nova Micro: 56.6 (#267), Claude Sonnet 4: 71.8 (#141)
| Benchmark | Amazon Nova Micro | Claude Sonnet 4 |
|---|---|---|
| IFEval | 76% | 84% |
| LMArena Instruction Following | 1174 | 1375 |
| LiveBench Instruction Following | 48% | — |
Long Context Amazon Nova Micro leads
Amazon Nova Micro: 36.5 (#224), Claude Sonnet 4: 33.6 (#254)
| Benchmark | Amazon Nova Micro | Claude Sonnet 4 |
|---|---|---|
| LMArena Longer Query | 1206 | 1398 |
| Fiction.LiveBench | — | 46.9% |
Writing & Preference Claude Sonnet 4 leads
Amazon Nova Micro: 39.7 (#242), Claude Sonnet 4: 57.3 (#127)
| Benchmark | Amazon Nova Micro | Claude Sonnet 4 |
|---|---|---|
| LMArena Text | 1208 | 1351 |
| LMArena Creative Writing | 1172 | 1345 |
| WildBench | 74.3% | 83.8% |
| LMArena Multi-Turn | 1178 | 1376 |
| Short-Story Creative Writing | — | 81.4% |
| EQ-Bench Creative Writing | — | 1483 |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Claude Sonnet 4?
Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 29.9 on the Noometry Index. Amazon Nova Micro costs 98× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Claude Sonnet 4?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Amazon Nova Micro or Claude Sonnet 4 better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 44.0 versus 30.0 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4 does, with 200K tokens against 128K.
How many benchmarks do Amazon Nova Micro and Claude Sonnet 4 share?
23 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Claude Sonnet 4 has 58.