Model comparison
Amazon Nova Micro vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 30.4 on the Noometry Index. Amazon Nova Micro costs 61× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Amazon Nova Micro scores higher in 1 category and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.4 to 26.9.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 128K.
Side by side
| Amazon Nova Micro | Qwen3.7 Max | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 30.4 | 51.5 |
| Released | 2024-12-03 | 2026-05-19 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1M |
| Max output | 10K | 131K |
| Input $ / M tokens | $0.035 | $2.50 |
| Output $ / M tokens | $0.14 | $7.50 |
| Results tracked | 32 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Amazon Nova Micro: 30.5 (#295), Qwen3.7 Max: 50.4 (#45)
| Benchmark | Amazon Nova Micro | Qwen3.7 Max |
|---|---|---|
| LMArena Coding | 1218 | 1498 |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| LiveBench Coding | 20.2% | — |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Too close to call
Amazon Nova Micro: 22.1 (#132), Qwen3.7 Max: 22.1 (#135)
| Benchmark | Amazon Nova Micro | Qwen3.7 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
Amazon Nova Micro: 17.4 (#294), Qwen3.7 Max: 49.2 (#38)
| Benchmark | Amazon Nova Micro | Qwen3.7 Max |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1483 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| LiveBench Reasoning | 25.1% | — |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 44% |
| Epoch Capabilities Index | — | 153.68 |
| LiveBench | 29.6% | — |
Math Qwen3.7 Max leads
Amazon Nova Micro: 26.9 (#254), Qwen3.7 Max: 62.4 (#32)
| Benchmark | Amazon Nova Micro | Qwen3.7 Max |
|---|---|---|
| LMArena Math | 1206 | 1490 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
Knowledge Qwen3.7 Max leads
Amazon Nova Micro: 29.6 (#237), Qwen3.7 Max: 61.6 (#28)
| Benchmark | Amazon Nova Micro | Qwen3.7 Max |
|---|---|---|
| LMArena Expert | 1184 | 1488 |
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |
| MMLU-Pro | 51.1% | — |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | 70.8% | — |
Multilingual Qwen3.7 Max leads
Amazon Nova Micro: 36.5 (#239), Qwen3.7 Max: 56.9 (#15)
| Benchmark | Amazon Nova Micro | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1186 | 1474 |
| LMArena Chinese | 1209 | 1530 |
| LMArena Russian | 1185 | 1484 |
| LMArena French | 1238 | — |
| LMArena German | 1192 | — |
| LMArena Japanese | 1154 | — |
| LMArena Korean | 1150 | — |
| LMArena Spanish | 1225 | — |
Instruction Following Qwen3.7 Max leads
Amazon Nova Micro: 56.3 (#272), Qwen3.7 Max: 76.7 (#38)
| Benchmark | Amazon Nova Micro | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1174 | 1460 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Qwen3.7 Max leads
Amazon Nova Micro: 36.5 (#229), Qwen3.7 Max: 45.4 (#40)
| Benchmark | Amazon Nova Micro | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1205 | 1482 |
Writing & Preference Qwen3.7 Max leads
Amazon Nova Micro: 39.5 (#247), Qwen3.7 Max: 65.0 (#54)
| Benchmark | Amazon Nova Micro | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1208 | 1476 |
| LMArena Creative Writing | 1172 | 1449 |
| LMArena Multi-Turn | 1178 | 1481 |
| WildBench | 74.3% | — |
| EQ-Bench 4 | — | 1110 |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 30.4 on the Noometry Index. Amazon Nova Micro costs 61× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Micro or Qwen3.7 Max?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is Amazon Nova Micro or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 30.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 128K.
How many benchmarks do Amazon Nova Micro and Qwen3.7 Max share?
12 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Qwen3.7 Max has 33.