Model comparison
Amazon Nova Micro vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 30.4 on the Noometry Index. Amazon Nova Micro costs 22× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and Qwen3.5 397B-A17B in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 29.6.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B accepts more context: 262K tokens versus 128K.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 30.4 | 46.0 |
| Released | 2024-12-03 | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 10K | 66K |
| Input $ / M tokens | $0.035 | $0.60 |
| Output $ / M tokens | $0.14 | $3.60 |
| Results tracked | 32 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Amazon Nova Micro: 30.5 (#295), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Amazon Nova Micro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1218 | 1465 |
| LMArena WebDev | — | 1400 |
| LiveBench Coding | 20.2% | — |
Agentic & Tool Use Qwen3.5 397B-A17B leads
Amazon Nova Micro: 22.1 (#132), Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Amazon Nova Micro | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| Berkeley Function Calling Leaderboard | 22.3% | — |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Qwen3.5 397B-A17B leads
Amazon Nova Micro: 17.4 (#294), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Amazon Nova Micro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1448 |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| LiveBench Reasoning | 25.1% | — |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 37.9% |
| Epoch Capabilities Index | — | 146.65 |
| LiveBench | 29.6% | — |
Math Qwen3.5 397B-A17B leads
Amazon Nova Micro: 26.9 (#254), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Amazon Nova Micro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Math | 1206 | 1454 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
Knowledge Qwen3.5 397B-A17B leads
Amazon Nova Micro: 29.6 (#237), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Amazon Nova Micro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Expert | 1184 | 1462 |
| GPQA Diamond | — | 86.4% |
| MMLU-Pro | 51.1% | — |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Amazon Nova Micro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Qwen3.5 397B-A17B leads
Amazon Nova Micro: 36.5 (#239), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Amazon Nova Micro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1186 | 1430 |
| LMArena Chinese | 1209 | 1500 |
| LMArena French | 1238 | 1461 |
| LMArena German | 1192 | 1447 |
| LMArena Japanese | 1154 | 1426 |
| LMArena Korean | 1150 | 1384 |
| LMArena Russian | 1185 | 1429 |
| LMArena Spanish | 1225 | 1441 |
Instruction Following Qwen3.5 397B-A17B leads
Amazon Nova Micro: 56.3 (#272), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Amazon Nova Micro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1174 | 1424 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Qwen3.5 397B-A17B leads
Amazon Nova Micro: 36.5 (#229), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Amazon Nova Micro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1205 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
Amazon Nova Micro: 39.5 (#247), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Amazon Nova Micro | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1208 | 1438 |
| LMArena Creative Writing | 1172 | 1401 |
| LMArena Multi-Turn | 1178 | 1446 |
| EQ-Bench Creative Writing | — | 1478 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 30.4 on the Noometry Index. Amazon Nova Micro costs 22× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Qwen3.5 397B-A17B?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.
Is Amazon Nova Micro or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 128K.
How many benchmarks do Amazon Nova Micro and Qwen3.5 397B-A17B share?
17 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Qwen3.5 397B-A17B has 36.