Model comparison
Amazon Nova Micro vs DeepSeek-R1-Distill-Qwen-32B
DeepSeek-R1-Distill-Qwen-32B is the stronger model overall, scoring 35.5 to 30.4 on the Noometry Index.
Last verified . 7 shared benchmarks.
DeepSeekSummary
- They share 7 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and DeepSeek-R1-Distill-Qwen-32B in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-R1-Distill-Qwen-32B leads 49.6 to 39.5.
- The biggest single-benchmark swing is LiveBench Reasoning: 25.1% for Amazon Nova Micro and 52.3% for DeepSeek-R1-Distill-Qwen-32B.
- DeepSeek-R1-Distill-Qwen-32B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | DeepSeek-R1-Distill-Qwen-32B | |
|---|---|---|
| Provider | Amazon | DeepSeek |
| Noometry Index | 30.4 | 35.5 |
| Released | 2024-12-03 | 2025-01-20 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.035 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 32 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1-Distill-Qwen-32B leads
Amazon Nova Micro: 30.5 (#295), DeepSeek-R1-Distill-Qwen-32B: 36.1 (#212)
| Benchmark | Amazon Nova Micro | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LiveBench Coding | 20.2% | 33.7% |
| BigCodeBench Instruct | — | 43.9% |
| LMArena Coding | 1218 | — |
| BigCodeBench Complete | — | 54.9% |
Agentic & Tool Use DeepSeek-R1-Distill-Qwen-32B leads
Amazon Nova Micro: 22.1 (#132), DeepSeek-R1-Distill-Qwen-32B: 28.1 (#94)
| Benchmark | Amazon Nova Micro | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
| BALROG | — | 19.5% |
Reasoning Too close to call
Amazon Nova Micro: 17.4 (#294), DeepSeek-R1-Distill-Qwen-32B: 18.2 (#284)
| Benchmark | Amazon Nova Micro | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LiveBench Reasoning | 25.1% | 52.3% |
| LiveBench Data Analysis | 34% | 45.4% |
| LiveBench | 29.6% | 45.5% |
| Chess Puzzles | — | 1% |
| LMArena Hard Prompts | 1191 | — |
| Epoch Capabilities Index | — | 137.44 |
Math DeepSeek-R1-Distill-Qwen-32B leads
Amazon Nova Micro: 26.9 (#254), DeepSeek-R1-Distill-Qwen-32B: 34.5 (#194)
| Benchmark | Amazon Nova Micro | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LiveBench Math | 34.5% | 59.4% |
| OTIS Mock AIME 2024-2025 | — | 55.6% |
| Omni-MATH | 21.4% | — |
| LMArena Math | 1206 | — |
Knowledge DeepSeek-R1-Distill-Qwen-32B leads
Amazon Nova Micro: 29.6 (#237), DeepSeek-R1-Distill-Qwen-32B: 35.7 (#182)
| Benchmark | Amazon Nova Micro | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| GPQA Diamond | — | 64.1% |
| MMLU-Pro | 51.1% | — |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| LMArena Expert | 1184 | — |
| MMLU | 70.8% | — |
Multilingual Not comparable
Amazon Nova Micro: 36.5 (#239), DeepSeek-R1-Distill-Qwen-32B: —
| Benchmark | Amazon Nova Micro | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LMArena Non-English | 1186 | — |
| LMArena Chinese | 1209 | — |
| LMArena French | 1238 | — |
| LMArena German | 1192 | — |
| LMArena Japanese | 1154 | — |
| LMArena Korean | 1150 | — |
| LMArena Russian | 1185 | — |
| LMArena Spanish | 1225 | — |
Instruction Following DeepSeek-R1-Distill-Qwen-32B leads
Amazon Nova Micro: 56.3 (#272), DeepSeek-R1-Distill-Qwen-32B: 61.6 (#243)
| Benchmark | Amazon Nova Micro | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LiveBench Instruction Following | 48% | 55.7% |
| IFEval | 76% | — |
| LMArena Instruction Following | 1174 | — |
Long Context Not comparable
Amazon Nova Micro: 36.5 (#229), DeepSeek-R1-Distill-Qwen-32B: —
| Benchmark | Amazon Nova Micro | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LMArena Longer Query | 1205 | — |
Writing & Preference DeepSeek-R1-Distill-Qwen-32B leads
Amazon Nova Micro: 39.5 (#247), DeepSeek-R1-Distill-Qwen-32B: 49.6 (#188)
| Benchmark | Amazon Nova Micro | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LiveBench Language | 15.8% | 26.8% |
| LMArena Text | 1208 | — |
| LMArena Creative Writing | 1172 | — |
| WildBench | 74.3% | — |
| LMArena Multi-Turn | 1178 | — |
Frequently asked questions
Is Amazon Nova Micro better than DeepSeek-R1-Distill-Qwen-32B?
DeepSeek-R1-Distill-Qwen-32B is the stronger model overall, scoring 35.5 to 30.4 on the Noometry Index.
Is Amazon Nova Micro or DeepSeek-R1-Distill-Qwen-32B better for coding?
DeepSeek-R1-Distill-Qwen-32B scores higher on coding benchmarks: 36.1 versus 30.5 in the Noometry coding category.
How many benchmarks do Amazon Nova Micro and DeepSeek-R1-Distill-Qwen-32B share?
7 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and DeepSeek-R1-Distill-Qwen-32B has 14.