Model comparison
Amazon Nova Pro vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 31.0 on the Noometry Index. Amazon Nova Pro costs 2.1× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Qwen3.8 Max in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 28.5.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 300K.
Side by side
| Amazon Nova Pro | Qwen3.8 Max | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 31.0 | 56.8 |
| Released | 2024-12-03 | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 1M |
| Max output | 10K | 131K |
| Input $ / M tokens | $0.80 | $2 |
| Output $ / M tokens | $3.20 | $6 |
| Results tracked | 38 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Amazon Nova Pro: 35.1 (#229), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Amazon Nova Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1270 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Qwen3.8 Max leads
Amazon Nova Pro: 16.7 (#147), Qwen3.8 Max: 45.4 (#14)
| Benchmark | Amazon Nova Pro | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Amazon Nova Pro: 20.0 (#243), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Amazon Nova Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1496 |
| Epoch Capabilities Index | 123.8 | 156.41 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 46.2% |
| LiveBench | 43.5% | — |
Math Qwen3.8 Max leads
Amazon Nova Pro: 28.5 (#243), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Amazon Nova Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1252 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
Knowledge Qwen3.8 Max leads
Amazon Nova Pro: 27.4 (#250), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Amazon Nova Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Expert | 1211 | 1507 |
| GPQA Diamond | — | 92.7% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 47.3% |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Qwen3.8 Max leads
Amazon Nova Pro: 25.0 (#126), Qwen3.8 Max: 37.2 (#75)
| Benchmark | Amazon Nova Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | 980 | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
Amazon Nova Pro: 39.7 (#223), Qwen3.8 Max: 56.7 (#18)
| Benchmark | Amazon Nova Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1234 | 1472 |
| LMArena Chinese | 1244 | 1538 |
| LMArena French | 1271 | 1503 |
| LMArena German | 1243 | 1483 |
| LMArena Japanese | 1200 | 1467 |
| LMArena Korean | 1203 | 1461 |
| LMArena Russian | 1240 | 1481 |
| LMArena Spanish | 1182 | 1492 |
Instruction Following Qwen3.8 Max leads
Amazon Nova Pro: 64.9 (#226), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Amazon Nova Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1235 | 1479 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Qwen3.8 Max leads
Amazon Nova Pro: 38.1 (#205), Qwen3.8 Max: 45.6 (#31)
| Benchmark | Amazon Nova Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1255 | 1489 |
Writing & Preference Qwen3.8 Max leads
Amazon Nova Pro: 43.9 (#226), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Amazon Nova Pro | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1259 | 1483 |
| LMArena Creative Writing | 1212 | 1479 |
| LMArena Multi-Turn | 1246 | 1489 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 31.0 on the Noometry Index. Amazon Nova Pro costs 2.1× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or Qwen3.8 Max?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Amazon Nova Pro or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 300K.
How many benchmarks do Amazon Nova Pro and Qwen3.8 Max share?
19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Qwen3.8 Max has 39.