Model comparison
Amazon Nova Micro vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 30.4 on the Noometry Index. Amazon Nova Micro costs 20× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Amazon Nova Micro scores higher in 1 category and Qwen3 235B-A22B in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 26.9.
- The biggest single-benchmark swing is Omni-MATH: 21.4% for Amazon Nova Micro and 71.8% for Qwen3 235B-A22B.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- Qwen3 235B-A22B accepts more context: 131K tokens versus 128K.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 30.4 | 43.5 |
| Released | 2024-12-03 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 128K | 131K |
| Max output | 10K | 16K |
| Input $ / M tokens | $0.035 | $0.70 |
| Output $ / M tokens | $0.14 | $2.80 |
| Results tracked | 32 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Amazon Nova Micro: 30.5 (#295), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Amazon Nova Micro | Qwen3 235B-A22B |
|---|---|---|
| LMArena Coding | 1218 | 1445 |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
| LiveBench Coding | 20.2% | — |
Agentic & Tool Use Qwen3 235B-A22B leads
Amazon Nova Micro: 22.1 (#132), Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Amazon Nova Micro | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Amazon Nova Micro leads
Amazon Nova Micro: 17.4 (#294), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Amazon Nova Micro | Qwen3 235B-A22B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1433 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| LiveBench Reasoning | 25.1% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 29.3% |
| Epoch Capabilities Index | — | 143.85 |
| ForecastBench | — | 59.7 |
| LiveBench | 29.6% | — |
Math Qwen3 235B-A22B leads
Amazon Nova Micro: 26.9 (#254), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Amazon Nova Micro | Qwen3 235B-A22B |
|---|---|---|
| Omni-MATH | 21.4% | 71.8% |
| LMArena Math | 1206 | 1432 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| LiveBench Math | 34.5% | — |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Amazon Nova Micro: 29.6 (#237), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Amazon Nova Micro | Qwen3 235B-A22B |
|---|---|---|
| MMLU-Pro | 51.1% | 84.4% |
| Vectara Hallucination Rate | 5.5% | 9.3% |
| GPQA (HELM) | 38.3% | 72.7% |
| LMArena Expert | 1184 | 1463 |
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| Confabulations | — | 15.6% |
| MMLU | 70.8% | — |
Multilingual Qwen3 235B-A22B leads
Amazon Nova Micro: 36.5 (#239), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Amazon Nova Micro | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1186 | 1409 |
| LMArena Chinese | 1209 | 1481 |
| LMArena French | 1238 | 1445 |
| LMArena German | 1192 | 1433 |
| LMArena Japanese | 1154 | 1399 |
| LMArena Korean | 1150 | 1391 |
| LMArena Russian | 1185 | 1411 |
| LMArena Spanish | 1225 | 1430 |
Instruction Following Qwen3 235B-A22B leads
Amazon Nova Micro: 56.3 (#272), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Amazon Nova Micro | Qwen3 235B-A22B |
|---|---|---|
| IFEval | 76% | 83.5% |
| LMArena Instruction Following | 1174 | 1408 |
| LiveBench Instruction Following | 48% | — |
Long Context Qwen3 235B-A22B leads
Amazon Nova Micro: 36.5 (#229), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Amazon Nova Micro | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1205 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
Amazon Nova Micro: 39.5 (#247), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Amazon Nova Micro | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1208 | 1419 |
| LMArena Creative Writing | 1172 | 1384 |
| WildBench | 74.3% | 86.6% |
| LMArena Multi-Turn | 1178 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 30.4 on the Noometry Index. Amazon Nova Micro costs 20× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Qwen3 235B-A22B?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Is Amazon Nova Micro or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3 235B-A22B does, with 131K tokens against 128K.
How many benchmarks do Amazon Nova Micro and Qwen3 235B-A22B share?
24 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Qwen3 235B-A22B has 49.