Model comparison
Amazon Nova Micro vs Qwen3.5 122B-A10B
Qwen3.5 122B-A10B is the stronger model overall, scoring 41.6 to 29.9 on the Noometry Index. Amazon Nova Micro costs 18× less per token, which makes it the better buy when Qwen3.5 122B-A10B'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 0 categories and Qwen3.5 122B-A10B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 122B-A10B leads 60.2 to 39.7.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.5% for Amazon Nova Micro and 11.2% for Qwen3.5 122B-A10B.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
- Qwen3.5 122B-A10B accepts more context: 262K tokens versus 128K.
- Qwen3.5 122B-A10B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 29.9 | 41.6 |
| Released | 2024-12-03 | 2026-02-23 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 10K | 66K |
| Input $ / M tokens | $0.035 | $0.40 |
| Output $ / M tokens | $0.14 | $3.20 |
| Results tracked | 32 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 122B-A10B leads
Amazon Nova Micro: 30.0 (#289), Qwen3.5 122B-A10B: 38.8 (#155)
| Benchmark | Amazon Nova Micro | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Coding | 1218 | 1436 |
| LMArena WebDev | — | 1360 |
| SciCode | — | 35.6% |
| LiveBench Coding | 20.2% | — |
Agentic & Tool Use Not comparable
Amazon Nova Micro: 21.9 (#125), Qwen3.5 122B-A10B: —
| Benchmark | Amazon Nova Micro | Qwen3.5 122B-A10B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
Reasoning Qwen3.5 122B-A10B leads
Amazon Nova Micro: 16.7 (#289), Qwen3.5 122B-A10B: 26.4 (#121)
| Benchmark | Amazon Nova Micro | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1421 |
| NYT Connections (extended) | — | 51.7% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 51.2% |
| LiveBench Reasoning | 25.1% | — |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84.3% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 32.2% |
| LiveBench | 29.6% | — |
Math Qwen3.5 122B-A10B leads
Amazon Nova Micro: 24.9 (#252), Qwen3.5 122B-A10B: 36.4 (#114)
| Benchmark | Amazon Nova Micro | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1206 | 1432 |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
Knowledge Qwen3.5 122B-A10B leads
Amazon Nova Micro: 29.2 (#231), Qwen3.5 122B-A10B: 38.2 (#138)
| Benchmark | Amazon Nova Micro | Qwen3.5 122B-A10B |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 11.2% |
| LMArena Expert | 1184 | 1431 |
| MMLU-Pro | 51.1% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multimodal Not comparable
Amazon Nova Micro: —, Qwen3.5 122B-A10B: 39.0 (#52)
| Benchmark | Amazon Nova Micro | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual Qwen3.5 122B-A10B leads
Amazon Nova Micro: 36.7 (#234), Qwen3.5 122B-A10B: 51.8 (#101)
| Benchmark | Amazon Nova Micro | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1186 | 1400 |
| LMArena Chinese | 1209 | 1462 |
| LMArena French | 1237 | 1442 |
| LMArena German | 1192 | 1425 |
| LMArena Japanese | 1154 | 1364 |
| LMArena Korean | 1150 | 1353 |
| LMArena Russian | 1185 | 1400 |
| LMArena Spanish | 1225 | 1423 |
Instruction Following Qwen3.5 122B-A10B leads
Amazon Nova Micro: 56.6 (#267), Qwen3.5 122B-A10B: 74.0 (#109)
| Benchmark | Amazon Nova Micro | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1174 | 1399 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Qwen3.5 122B-A10B leads
Amazon Nova Micro: 36.5 (#224), Qwen3.5 122B-A10B: 43.0 (#105)
| Benchmark | Amazon Nova Micro | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1206 | 1410 |
Writing & Preference Qwen3.5 122B-A10B leads
Amazon Nova Micro: 39.7 (#242), Qwen3.5 122B-A10B: 60.2 (#98)
| Benchmark | Amazon Nova Micro | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1208 | 1417 |
| LMArena Creative Writing | 1172 | 1369 |
| LMArena Multi-Turn | 1178 | 1416 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is the stronger model overall, scoring 41.6 to 29.9 on the Noometry Index. Amazon Nova Micro costs 18× less per token, which makes it the better buy when Qwen3.5 122B-A10B's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Qwen3.5 122B-A10B?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Qwen3.5 122B-A10B lists at $0.40 and $3.20.
Is Amazon Nova Micro or Qwen3.5 122B-A10B better for coding?
Qwen3.5 122B-A10B scores higher on coding benchmarks: 38.8 versus 30.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 122B-A10B does, with 262K tokens against 128K.
How many benchmarks do Amazon Nova Micro and Qwen3.5 122B-A10B share?
18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Qwen3.5 122B-A10B has 27.