Model comparison
Amazon Nova Micro vs Claude 3.5 Sonnet
Claude 3.5 Sonnet is the stronger model overall, scoring 34.4 to 29.9 on the Noometry Index.
Last verified . 30 shared benchmarks.
Summary
- They share 30 benchmarks with published results for both. Amazon Nova Micro scores higher in 2 categories and Claude 3.5 Sonnet in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3.5 Sonnet leads 53.0 to 39.7.
- The biggest single-benchmark swing is LiveBench Coding: 20.2% for Amazon Nova Micro and 67.1% for Claude 3.5 Sonnet.
Side by side
| Amazon Nova Micro | Claude 3.5 Sonnet | |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 29.9 | 34.4 |
| Released | 2024-12-03 | 2024-06-20 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.035 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 32 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Amazon Nova Micro: 30.0 (#289), Claude 3.5 Sonnet: 39.5 (#145)
| Benchmark | Amazon Nova Micro | Claude 3.5 Sonnet |
|---|---|---|
| LiveBench Coding | 20.2% | 67.1% |
| LMArena Coding | 1218 | 1343 |
| Aider Polyglot | — | 51.6% |
| GSO | — | 4.6% |
| WeirdML | — | 40% |
| BigCodeBench Instruct | — | 46.8% |
| BigCodeBench Complete | — | 58.6% |
| CadEval | — | 48% |
| HumanEval+ | — | 81.7% |
| MBPP+ | — | 74.3% |
Agentic & Tool Use Claude 3.5 Sonnet leads
Amazon Nova Micro: 21.9 (#125), Claude 3.5 Sonnet: 32.1 (#61)
| Benchmark | Amazon Nova Micro | Claude 3.5 Sonnet |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
| TheAgentCompany | — | 24% |
| Cybench | — | 17.5% |
| BALROG | — | 32.6% |
| METR Time Horizons | — | 45.2% |
Reasoning Claude 3.5 Sonnet leads
Amazon Nova Micro: 16.7 (#289), Claude 3.5 Sonnet: 22.5 (#176)
| Benchmark | Amazon Nova Micro | Claude 3.5 Sonnet |
|---|---|---|
| LiveBench Reasoning | 25.1% | 56.7% |
| LMArena Hard Prompts | 1191 | 1305 |
| LiveBench Data Analysis | 34% | 55% |
| LiveBench | 29.6% | 59% |
| SimpleBench | — | 41.4% |
| EnigmaEval | — | 0.9% |
| DTBench | — | 67.8% |
| Epoch Capabilities Index | — | 133.55 |
| ForecastBench | — | 60.7 |
Math Amazon Nova Micro leads
Amazon Nova Micro: 24.9 (#252), Claude 3.5 Sonnet: 18.0 (#282)
| Benchmark | Amazon Nova Micro | Claude 3.5 Sonnet |
|---|---|---|
| Omni-MATH | 21.4% | 27.6% |
| LiveBench Math | 34.5% | 52.3% |
| LMArena Math | 1206 | 1306 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| MATH Level 5 | — | 56.9% |
| FrontierMath (Feb 2025 set) | — | 2.1% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Too close to call
Amazon Nova Micro: 29.2 (#231), Claude 3.5 Sonnet: 28.5 (#236)
| Benchmark | Amazon Nova Micro | Claude 3.5 Sonnet |
|---|---|---|
| MMLU-Pro | 51.1% | 77.7% |
| GPQA (HELM) | 38.3% | 56.5% |
| LMArena Expert | 1184 | 1264 |
| MMLU | 70.8% | 87.3% |
| GPQA Diamond | — | 55.3% |
| Humanity's Last Exam | — | 4.1% |
| Confabulations | — | 19.9% |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Not comparable
Amazon Nova Micro: —, Claude 3.5 Sonnet: 26.0 (#115)
| Benchmark | Amazon Nova Micro | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Vision | — | 1125 |
| Video-MME | — | 60% |
| GeoBench | — | 62% |
| VPCT | — | 33% |
Multilingual Claude 3.5 Sonnet leads
Amazon Nova Micro: 36.7 (#234), Claude 3.5 Sonnet: 43.4 (#180)
| Benchmark | Amazon Nova Micro | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Non-English | 1186 | 1283 |
| LMArena Chinese | 1209 | 1271 |
| LMArena French | 1237 | 1304 |
| LMArena German | 1192 | 1297 |
| LMArena Japanese | 1154 | 1234 |
| LMArena Korean | 1150 | 1200 |
| LMArena Russian | 1185 | 1305 |
| LMArena Spanish | 1225 | 1289 |
Instruction Following Claude 3.5 Sonnet leads
Amazon Nova Micro: 56.6 (#267), Claude 3.5 Sonnet: 69.0 (#177)
| Benchmark | Amazon Nova Micro | Claude 3.5 Sonnet |
|---|---|---|
| LiveBench Instruction Following | 48% | 69.3% |
| IFEval | 76% | 85.5% |
| LMArena Instruction Following | 1174 | 1297 |
Long Context Claude 3.5 Sonnet leads
Amazon Nova Micro: 36.5 (#224), Claude 3.5 Sonnet: 39.9 (#162)
| Benchmark | Amazon Nova Micro | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Longer Query | 1206 | 1311 |
Writing & Preference Claude 3.5 Sonnet leads
Amazon Nova Micro: 39.7 (#242), Claude 3.5 Sonnet: 53.0 (#159)
| Benchmark | Amazon Nova Micro | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Text | 1208 | 1298 |
| LMArena Creative Writing | 1172 | 1292 |
| WildBench | 74.3% | 79.2% |
| LMArena Multi-Turn | 1178 | 1326 |
| LiveBench Language | 15.8% | 53.8% |
| Short-Story Creative Writing | — | 80.3% |
| EQ-Bench Creative Writing | — | 1451 |
Frequently asked questions
Is Amazon Nova Micro better than Claude 3.5 Sonnet?
Claude 3.5 Sonnet is the stronger model overall, scoring 34.4 to 29.9 on the Noometry Index.
Is Amazon Nova Micro or Claude 3.5 Sonnet better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.5 versus 30.0 in the Noometry coding category.
How many benchmarks do Amazon Nova Micro and Claude 3.5 Sonnet share?
30 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Claude 3.5 Sonnet has 60.