# Amazon Nova Pro vs Qwen3 235B-A22B

> Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 31.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-qwen3-235b-a22b
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Amazon Nova Pro scores higher in 1 category and Qwen3 235B-A22B in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.6 to 27.4.
- The biggest single-benchmark swing is Omni-MATH: 24.2% for Amazon Nova Pro and 71.8% for Qwen3 235B-A22B.
- Qwen3 235B-A22B 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 235B-A22B has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Pro | Qwen3 235B-A22B |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 31.0 | 43.5 |
| Rank | 281 | 91 |
| Context | 300K | 131K |
| Input $/M | $0.80 | $0.70 |
| Output $/M | $3.20 | $2.80 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Pro: 35.1 (#229)
- Qwen3 235B-A22B: 44.3 (#75)

| Benchmark | Amazon Nova Pro | Qwen3 235B-A22B |
|---|---|---|
| LMArena Coding | 1270 | 1445 |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
| LiveBench Coding | 38.1% | — |

## Agentic & Tool Use

- Amazon Nova Pro: 16.7 (#147)
- Qwen3 235B-A22B: 33.9 (#51)

| Benchmark | Amazon Nova Pro | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 52.1% |
| TheAgentCompany | 1.7% | — |
| Vending-Bench 2 | — | -11.34 |

## Reasoning

- Amazon Nova Pro: 20.0 (#243)
- Qwen3 235B-A22B: 15.7 (#311)

| Benchmark | Amazon Nova Pro | Qwen3 235B-A22B |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1433 |
| Epoch Capabilities Index | 123.8 | 143.85 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 29.3% |
| ForecastBench | — | 59.7 |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 28.5 (#243)
- Qwen3 235B-A22B: 50.4 (#57)

| Benchmark | Amazon Nova Pro | Qwen3 235B-A22B |
|---|---|---|
| Omni-MATH | 24.2% | 71.8% |
| LMArena Math | 1252 | 1432 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Amazon Nova Pro: 27.4 (#250)
- Qwen3 235B-A22B: 49.6 (#73)

| Benchmark | Amazon Nova Pro | Qwen3 235B-A22B |
|---|---|---|
| MMLU-Pro | 67.3% | 84.4% |
| Confabulations | 30.1% | 15.6% |
| Vectara Hallucination Rate | 5.1% | 9.3% |
| GPQA (HELM) | 44.6% | 72.7% |
| LMArena Expert | 1211 | 1463 |
| GPQA Diamond | — | 80.1% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 40.4% |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 25.0 (#126)
- Qwen3 235B-A22B: —

| Benchmark | Amazon Nova Pro | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 980 | — |

## Multilingual

- Amazon Nova Pro: 39.7 (#223)
- Qwen3 235B-A22B: 52.3 (#89)

| Benchmark | Amazon Nova Pro | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1234 | 1409 |
| LMArena Chinese | 1244 | 1481 |
| LMArena French | 1271 | 1445 |
| LMArena German | 1243 | 1433 |
| LMArena Japanese | 1200 | 1399 |
| LMArena Korean | 1203 | 1391 |
| LMArena Russian | 1240 | 1411 |
| LMArena Spanish | 1182 | 1430 |

## Instruction Following

- Amazon Nova Pro: 64.9 (#226)
- Qwen3 235B-A22B: 72.6 (#136)

| Benchmark | Amazon Nova Pro | Qwen3 235B-A22B |
|---|---|---|
| IFEval | 81.5% | 83.5% |
| LMArena Instruction Following | 1235 | 1408 |
| LiveBench Instruction Following | 67.1% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#205)
- Qwen3 235B-A22B: 46.1 (#26)

| Benchmark | Amazon Nova Pro | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1255 | 1426 |
| Fiction.LiveBench | — | 75% |

## Writing & Preference

- Amazon Nova Pro: 43.9 (#226)
- Qwen3 235B-A22B: 59.6 (#108)

| Benchmark | Amazon Nova Pro | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1259 | 1419 |
| LMArena Creative Writing | 1212 | 1384 |
| Short-Story Creative Writing | 60.5% | 83% |
| WildBench | 77.7% | 86.6% |
| LMArena Multi-Turn | 1246 | 1432 |
| EQ-Bench Creative Writing | — | 1366 |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than Qwen3 235B-A22B?

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 31.0 on the Noometry Index.

### Which is cheaper, Amazon Nova Pro or Qwen3 235B-A22B?

Qwen3 235B-A22B 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 235B-A22B better for coding?

Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 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 235B-A22B share?

27 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Qwen3 235B-A22B has 49.