Model comparison
Amazon Nova Pro vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 31.0 on the Noometry Index.
Last verified . 16 shared benchmarks.
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Qwen3 32B in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Qwen3 32B leads 32.6 to 16.7.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 25% for Amazon Nova Pro and 48.7% for Qwen3 32B.
- Qwen3 32B is cheaper at $0.70 / $2.80 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 131K.
- Qwen3 32B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Qwen3 32B | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 31.0 | 39.2 |
| Released | 2024-12-03 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 300K | 131K |
| Max output | 10K | 16K |
| Input $ / M tokens | $0.80 | $0.70 |
| Output $ / M tokens | $3.20 | $2.80 |
| Results tracked | 38 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Amazon Nova Pro: 35.1 (#229), Qwen3 32B: 37.7 (#190)
| Benchmark | Amazon Nova Pro | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1270 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Qwen3 32B leads
Amazon Nova Pro: 16.7 (#147), Qwen3 32B: 32.6 (#62)
| Benchmark | Amazon Nova Pro | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 48.7% |
| TheAgentCompany | 1.7% | — |
Reasoning Too close to call
Amazon Nova Pro: 20.0 (#243), Qwen3 32B: 20.2 (#241)
| Benchmark | Amazon Nova Pro | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1334 |
| Epoch Capabilities Index | 123.8 | 138.51 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 67.5% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 17.3% |
| LiveBench | 43.5% | — |
Math Qwen3 32B leads
Amazon Nova Pro: 28.5 (#243), Qwen3 32B: 39.7 (#99)
| Benchmark | Amazon Nova Pro | Qwen3 32B |
|---|---|---|
| LMArena Math | 1252 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge Qwen3 32B leads
Amazon Nova Pro: 27.4 (#250), Qwen3 32B: 40.0 (#125)
| Benchmark | Amazon Nova Pro | Qwen3 32B |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 5.9% |
| LMArena Expert | 1211 | 1362 |
| GPQA Diamond | — | 65.7% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Qwen3 32B: —
| Benchmark | Amazon Nova Pro | Qwen3 32B |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Qwen3 32B leads
Amazon Nova Pro: 39.7 (#223), Qwen3 32B: 45.6 (#167)
| Benchmark | Amazon Nova Pro | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1234 | 1317 |
| LMArena Chinese | 1244 | 1357 |
| LMArena German | 1243 | 1341 |
| LMArena Russian | 1240 | 1311 |
| LMArena French | 1271 | — |
| LMArena Japanese | 1200 | — |
| LMArena Korean | 1203 | — |
| LMArena Spanish | 1182 | — |
Instruction Following Qwen3 32B leads
Amazon Nova Pro: 64.9 (#226), Qwen3 32B: 68.9 (#179)
| Benchmark | Amazon Nova Pro | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1235 | 1305 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Qwen3 32B leads
Amazon Nova Pro: 38.1 (#205), Qwen3 32B: 43.8 (#87)
| Benchmark | Amazon Nova Pro | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1255 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Amazon Nova Pro: 43.9 (#226), Qwen3 32B: 52.9 (#163)
| Benchmark | Amazon Nova Pro | Qwen3 32B |
|---|---|---|
| LMArena Text | 1259 | 1340 |
| LMArena Creative Writing | 1212 | 1297 |
| LMArena Multi-Turn | 1246 | 1331 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or Qwen3 32B?
Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.7 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 131K.
How many benchmarks do Amazon Nova Pro and Qwen3 32B share?
16 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Qwen3 32B has 26.