Model comparison
Amazon Nova Micro vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 29.9 on the Noometry Index. Amazon Nova Micro costs 3.5× less per token, which makes it the better buy when Qwen3-30B-A3B's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Amazon Nova Micro scores higher in 1 category and Qwen3-30B-A3B in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3-30B-A3B leads 55.9 to 39.7.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 22.3% for Amazon Nova Micro and 41.4% for Qwen3-30B-A3B.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.12 / $0.50 for Qwen3-30B-A3B.
- Amazon Nova Micro accepts more context: 128K tokens versus 41K.
- Qwen3-30B-A3B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 29.9 | 38.5 |
| Released | 2024-12-03 | 2025-04-28 |
| Weights | Proprietary | Open |
| Context window | 128K | 41K |
| Max output | 10K | 16K |
| Input $ / M tokens | $0.035 | $0.12 |
| Output $ / M tokens | $0.14 | $0.50 |
| Results tracked | 32 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-30B-A3B leads
Amazon Nova Micro: 30.0 (#289), Qwen3-30B-A3B: 37.0 (#188)
| Benchmark | Amazon Nova Micro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1218 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
| LiveBench Coding | 20.2% | — |
Agentic & Tool Use Qwen3-30B-A3B leads
Amazon Nova Micro: 21.9 (#125), Qwen3-30B-A3B: 29.5 (#75)
| Benchmark | Amazon Nova Micro | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | 41.4% |
Reasoning Qwen3-30B-A3B leads
Amazon Nova Micro: 16.7 (#289), Qwen3-30B-A3B: 21.6 (#193)
| Benchmark | Amazon Nova Micro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1398 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| LiveBench Reasoning | 25.1% | — |
| DTBench | — | 69.3% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 22.4% |
| Epoch Capabilities Index | — | 139.63 |
| LiveBench | 29.6% | — |
Math Qwen3-30B-A3B leads
Amazon Nova Micro: 24.9 (#252), Qwen3-30B-A3B: 36.0 (#133)
| Benchmark | Amazon Nova Micro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1206 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
Knowledge Qwen3-30B-A3B leads
Amazon Nova Micro: 29.2 (#231), Qwen3-30B-A3B: 41.7 (#96)
| Benchmark | Amazon Nova Micro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1184 | 1395 |
| GPQA Diamond | — | 70.1% |
| MMLU-Pro | 51.1% | — |
| Confabulations | — | 12.3% |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multilingual Qwen3-30B-A3B leads
Amazon Nova Micro: 36.7 (#234), Qwen3-30B-A3B: 49.8 (#126)
| Benchmark | Amazon Nova Micro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1186 | 1372 |
| LMArena Chinese | 1209 | 1434 |
| LMArena French | 1237 | 1419 |
| LMArena German | 1192 | 1379 |
| LMArena Japanese | 1154 | 1338 |
| LMArena Korean | 1150 | 1333 |
| LMArena Russian | 1185 | 1369 |
| LMArena Spanish | 1225 | 1403 |
Instruction Following Qwen3-30B-A3B leads
Amazon Nova Micro: 56.6 (#267), Qwen3-30B-A3B: 72.2 (#137)
| Benchmark | Amazon Nova Micro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1174 | 1364 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Amazon Nova Micro leads
Amazon Nova Micro: 36.5 (#224), Qwen3-30B-A3B: 31.0 (#278)
| Benchmark | Amazon Nova Micro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1206 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Qwen3-30B-A3B leads
Amazon Nova Micro: 39.7 (#242), Qwen3-30B-A3B: 55.9 (#138)
| Benchmark | Amazon Nova Micro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1208 | 1384 |
| LMArena Creative Writing | 1172 | 1318 |
| LMArena Multi-Turn | 1178 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 29.9 on the Noometry Index. Amazon Nova Micro costs 3.5× less per token, which makes it the better buy when Qwen3-30B-A3B's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Qwen3-30B-A3B?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Qwen3-30B-A3B lists at $0.12 and $0.50.
Is Amazon Nova Micro or Qwen3-30B-A3B better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.0 versus 30.0 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Micro does, with 128K tokens against 41K.
How many benchmarks do Amazon Nova Micro and Qwen3-30B-A3B share?
18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Qwen3-30B-A3B has 32.