Model comparison
Amazon Nova Micro vs DeepSeek-V3.1
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 29.9 on the Noometry Index. Amazon Nova Micro costs 6.9× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
DeepSeekSummary
- They share 18 benchmarks with published results for both. Amazon Nova Micro scores higher in 1 category and DeepSeek-V3.1 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.5 to 39.7.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
- DeepSeek-V3.1 accepts more context: 164K tokens versus 128K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | DeepSeek-V3.1 | |
|---|---|---|
| Provider | Amazon | DeepSeek |
| Noometry Index | 29.9 | 42.2 |
| Released | 2024-12-03 | 2025-08-21 |
| Weights | Proprietary | Open |
| Context window | 128K | 164K |
| Max output | 10K | 8K |
| Input $ / M tokens | $0.035 | $0.25 |
| Output $ / M tokens | $0.14 | $0.95 |
| Results tracked | 32 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
Amazon Nova Micro: 30.0 (#289), DeepSeek-V3.1: 39.8 (#140)
| Benchmark | Amazon Nova Micro | DeepSeek-V3.1 |
|---|---|---|
| LMArena Coding | 1218 | 1417 |
| WeirdML | — | 38.4% |
| LiveBench Coding | 20.2% | — |
Agentic & Tool Use Not comparable
Amazon Nova Micro: 21.9 (#125), DeepSeek-V3.1: —
| Benchmark | Amazon Nova Micro | DeepSeek-V3.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
Reasoning DeepSeek-V3.1 leads
Amazon Nova Micro: 16.7 (#289), DeepSeek-V3.1: 27.3 (#109)
| Benchmark | Amazon Nova Micro | DeepSeek-V3.1 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1417 |
| SimpleBench | — | 40% |
| Kagi LLM Benchmark | — | 53.2% |
| LiveBench Reasoning | 25.1% | — |
| DTBench | — | 82.7% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 24.3% |
| Epoch Capabilities Index | — | 139.92 |
| ForecastBench | — | 58 |
| LiveBench | 29.6% | — |
Math DeepSeek-V3.1 leads
Amazon Nova Micro: 24.9 (#252), DeepSeek-V3.1: 36.1 (#125)
| Benchmark | Amazon Nova Micro | DeepSeek-V3.1 |
|---|---|---|
| LMArena Math | 1206 | 1420 |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
Knowledge DeepSeek-V3.1 leads
Amazon Nova Micro: 29.2 (#231), DeepSeek-V3.1: 43.0 (#86)
| Benchmark | Amazon Nova Micro | DeepSeek-V3.1 |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 5.5% |
| LMArena Expert | 1184 | 1403 |
| MMLU-Pro | 51.1% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multilingual DeepSeek-V3.1 leads
Amazon Nova Micro: 36.7 (#234), DeepSeek-V3.1: 51.8 (#100)
| Benchmark | Amazon Nova Micro | DeepSeek-V3.1 |
|---|---|---|
| LMArena Non-English | 1186 | 1400 |
| LMArena Chinese | 1209 | 1470 |
| LMArena French | 1237 | 1447 |
| LMArena German | 1192 | 1412 |
| LMArena Japanese | 1154 | 1374 |
| LMArena Korean | 1150 | 1337 |
| LMArena Russian | 1185 | 1405 |
| LMArena Spanish | 1225 | 1429 |
Instruction Following DeepSeek-V3.1 leads
Amazon Nova Micro: 56.6 (#267), DeepSeek-V3.1: 74.1 (#105)
| Benchmark | Amazon Nova Micro | DeepSeek-V3.1 |
|---|---|---|
| LMArena Instruction Following | 1174 | 1400 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Too close to call
Amazon Nova Micro: 36.5 (#224), DeepSeek-V3.1: 36.3 (#227)
| Benchmark | Amazon Nova Micro | DeepSeek-V3.1 |
|---|---|---|
| LMArena Longer Query | 1206 | 1422 |
| Fiction.LiveBench | — | 52.8% |
Writing & Preference DeepSeek-V3.1 leads
Amazon Nova Micro: 39.7 (#242), DeepSeek-V3.1: 60.5 (#93)
| Benchmark | Amazon Nova Micro | DeepSeek-V3.1 |
|---|---|---|
| LMArena Text | 1208 | 1420 |
| LMArena Creative Writing | 1172 | 1401 |
| LMArena Multi-Turn | 1178 | 1408 |
| EQ-Bench Creative Writing | — | 1436 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than DeepSeek-V3.1?
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 29.9 on the Noometry Index. Amazon Nova Micro costs 6.9× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or DeepSeek-V3.1?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; DeepSeek-V3.1 lists at $0.25 and $0.95.
Is Amazon Nova Micro or DeepSeek-V3.1 better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 30.0 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1 does, with 164K tokens against 128K.
How many benchmarks do Amazon Nova Micro and DeepSeek-V3.1 share?
18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and DeepSeek-V3.1 has 27.