Model comparison
Amazon Nova Micro vs DeepSeek-R1
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 30.4 on the Noometry Index. Amazon Nova Micro costs 15× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
DeepSeekSummary
- They share 30 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and DeepSeek-R1 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-R1 leads 61.4 to 39.5.
- The biggest single-benchmark swing is LiveBench Reasoning: 25.1% for Amazon Nova Micro and 83.2% for DeepSeek-R1.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- DeepSeek-R1 accepts more context: 164K tokens versus 128K.
Side by side
| Amazon Nova Micro | DeepSeek-R1 | |
|---|---|---|
| Provider | Amazon | DeepSeek |
| Noometry Index | 30.4 | 42.3 |
| Released | 2024-12-03 | 2025-01-20 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 164K |
| Max output | 10K | 64K |
| Input $ / M tokens | $0.035 | $0.50 |
| Output $ / M tokens | $0.14 | $2.15 |
| Results tracked | 32 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
Amazon Nova Micro: 30.5 (#295), DeepSeek-R1: 46.3 (#68)
| Benchmark | Amazon Nova Micro | DeepSeek-R1 |
|---|---|---|
| LiveBench Coding | 20.2% | 66.7% |
| LMArena Coding | 1218 | 1427 |
| Aider Polyglot | — | 71.4% |
| SciCode | — | 35.7% |
| WeirdML | — | 41.6% |
| ALE-Bench | — | 804.12 |
| AlgoTune | — | 1.7 |
Agentic & Tool Use DeepSeek-R1 leads
Amazon Nova Micro: 22.1 (#132), DeepSeek-R1: 30.7 (#75)
| Benchmark | Amazon Nova Micro | DeepSeek-R1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
| DeepResearch Bench | — | 35.1% |
| BALROG | — | 34.9% |
| METR Time Horizons | — | 53.8% |
Reasoning DeepSeek-R1 leads
Amazon Nova Micro: 17.4 (#294), DeepSeek-R1: 18.6 (#278)
| Benchmark | Amazon Nova Micro | DeepSeek-R1 |
|---|---|---|
| LiveBench Reasoning | 25.1% | 83.2% |
| LMArena Hard Prompts | 1191 | 1416 |
| LiveBench Data Analysis | 34% | 69.8% |
| LiveBench | 29.6% | 71.6% |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 40.8% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 21.2% |
| CritPt | — | 1.1% |
| Epoch Capabilities Index | — | 141.29 |
| ForecastBench | — | 60 |
Math DeepSeek-R1 leads
Amazon Nova Micro: 26.9 (#254), DeepSeek-R1: 43.8 (#79)
| Benchmark | Amazon Nova Micro | DeepSeek-R1 |
|---|---|---|
| Omni-MATH | 21.4% | 42.4% |
| LiveBench Math | 34.5% | 80.7% |
| LMArena Math | 1206 | 1400 |
| OTIS Mock AIME 2024-2025 | — | 66.4% |
| MATH Level 5 | — | 96.6% |
Knowledge DeepSeek-R1 leads
Amazon Nova Micro: 29.6 (#237), DeepSeek-R1: 44.5 (#87)
| Benchmark | Amazon Nova Micro | DeepSeek-R1 |
|---|---|---|
| MMLU-Pro | 51.1% | 79.3% |
| Vectara Hallucination Rate | 5.5% | 11.3% |
| GPQA (HELM) | 38.3% | 66.6% |
| LMArena Expert | 1184 | 1394 |
| GPQA Diamond | — | 76.3% |
| Confabulations | — | 12.7% |
| MMLU | 70.8% | — |
Multilingual DeepSeek-R1 leads
Amazon Nova Micro: 36.5 (#239), DeepSeek-R1: 52.4 (#85)
| Benchmark | Amazon Nova Micro | DeepSeek-R1 |
|---|---|---|
| LMArena Non-English | 1186 | 1412 |
| LMArena Chinese | 1209 | 1442 |
| LMArena French | 1238 | 1417 |
| LMArena German | 1192 | 1404 |
| LMArena Japanese | 1154 | 1391 |
| LMArena Korean | 1150 | 1360 |
| LMArena Russian | 1185 | 1423 |
| LMArena Spanish | 1225 | 1411 |
Instruction Following DeepSeek-R1 leads
Amazon Nova Micro: 56.3 (#272), DeepSeek-R1: 72.0 (#143)
| Benchmark | Amazon Nova Micro | DeepSeek-R1 |
|---|---|---|
| LiveBench Instruction Following | 48% | 80.5% |
| IFEval | 76% | 78.4% |
| LMArena Instruction Following | 1174 | 1382 |
Long Context DeepSeek-R1 leads
Amazon Nova Micro: 36.5 (#229), DeepSeek-R1: 45.4 (#36)
| Benchmark | Amazon Nova Micro | DeepSeek-R1 |
|---|---|---|
| LMArena Longer Query | 1205 | 1391 |
| Fiction.LiveBench | — | 75% |
Writing & Preference DeepSeek-R1 leads
Amazon Nova Micro: 39.5 (#247), DeepSeek-R1: 61.4 (#88)
| Benchmark | Amazon Nova Micro | DeepSeek-R1 |
|---|---|---|
| LMArena Text | 1208 | 1428 |
| LMArena Creative Writing | 1172 | 1405 |
| WildBench | 74.3% | 82.8% |
| LMArena Multi-Turn | 1178 | 1405 |
| LiveBench Language | 15.8% | 48.5% |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1500 |
Frequently asked questions
Is Amazon Nova Micro better than DeepSeek-R1?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 30.4 on the Noometry Index. Amazon Nova Micro costs 15× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or DeepSeek-R1?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.
Is Amazon Nova Micro or DeepSeek-R1 better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-R1 does, with 164K tokens against 128K.
How many benchmarks do Amazon Nova Micro and DeepSeek-R1 share?
30 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and DeepSeek-R1 has 52.