# Amazon Nova Pro vs Qwen3-30B-A3B

> Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 31.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-pro-vs-qwen3-30b-a3b
- Last updated: 2026-10-12
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Amazon Nova Pro scores higher in 1 category and Qwen3-30B-A3B in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-30B-A3B leads 41.8 to 27.4.
- The biggest single-benchmark swing is Confabulations: 30.1% for Amazon Nova Pro and 12.3% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 41K.
- Qwen3-30B-A3B has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Pro | Qwen3-30B-A3B |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 31.0 | 38.9 |
| Rank | 281 | 179 |
| Context | 300K | 41K |
| Input $/M | $0.80 | $0.12 |
| Output $/M | $3.20 | $0.50 |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Pro: 35.1 (#229)
- Qwen3-30B-A3B: 37.5 (#194)

| Benchmark | Amazon Nova Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1270 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
| LiveBench Coding | 38.1% | — |

## Agentic & Tool Use

- Amazon Nova Pro: 16.7 (#147)
- Qwen3-30B-A3B: 29.8 (#82)

| Benchmark | Amazon Nova Pro | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 41.4% |
| TheAgentCompany | 1.7% | — |

## Reasoning

- Amazon Nova Pro: 20.0 (#243)
- Qwen3-30B-A3B: 22.2 (#204)

| Benchmark | Amazon Nova Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1398 |
| Epoch Capabilities Index | 123.8 | 139.63 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 69.3% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 22.4% |
| LiveBench | 43.5% | — |

## Math

- Amazon Nova Pro: 28.5 (#243)
- Qwen3-30B-A3B: 37.4 (#157)

| Benchmark | Amazon Nova Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1252 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |

## Knowledge

- Amazon Nova Pro: 27.4 (#250)
- Qwen3-30B-A3B: 41.8 (#105)

| Benchmark | Amazon Nova Pro | Qwen3-30B-A3B |
|---|---|---|
| Confabulations | 30.1% | 12.3% |
| LMArena Expert | 1211 | 1396 |
| GPQA Diamond | — | 70.1% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |

## Multimodal

- Amazon Nova Pro: 25.0 (#126)
- Qwen3-30B-A3B: —

| Benchmark | Amazon Nova Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Vision | 980 | — |

## Multilingual

- Amazon Nova Pro: 39.7 (#223)
- Qwen3-30B-A3B: 49.5 (#132)

| Benchmark | Amazon Nova Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1234 | 1372 |
| LMArena Chinese | 1244 | 1433 |
| LMArena French | 1271 | 1418 |
| LMArena German | 1243 | 1380 |
| LMArena Japanese | 1200 | 1337 |
| LMArena Korean | 1203 | 1331 |
| LMArena Russian | 1240 | 1370 |
| LMArena Spanish | 1182 | 1404 |

## Instruction Following

- Amazon Nova Pro: 64.9 (#226)
- Qwen3-30B-A3B: 72.0 (#142)

| Benchmark | Amazon Nova Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1235 | 1363 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |

## Long Context

- Amazon Nova Pro: 38.1 (#205)
- Qwen3-30B-A3B: 31.0 (#283)

| Benchmark | Amazon Nova Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1255 | 1379 |
| Fiction.LiveBench | — | 40.6% |

## Writing & Preference

- Amazon Nova Pro: 43.9 (#226)
- Qwen3-30B-A3B: 55.6 (#143)

| Benchmark | Amazon Nova Pro | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1259 | 1384 |
| LMArena Creative Writing | 1212 | 1317 |
| Short-Story Creative Writing | 60.5% | 75.3% |
| LMArena Multi-Turn | 1246 | 1378 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |

## FAQ

### Is Amazon Nova Pro better than Qwen3-30B-A3B?

Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 31.0 on the Noometry Index.

### Which is cheaper, Amazon Nova Pro or Qwen3-30B-A3B?

Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.

### Is Amazon Nova Pro or Qwen3-30B-A3B better for coding?

Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 35.1 in the Noometry coding category.

### Which has the bigger context window?

Amazon Nova Pro does, with 300K tokens against 41K.

### How many benchmarks do Amazon Nova Pro and Qwen3-30B-A3B share?

21 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Qwen3-30B-A3B has 32.