# Amazon Nova Experimental Chat 10 20 vs Qwen2-72B

> Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 42.1 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-experimental-chat-10-20-vs-qwen2-72b
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Amazon Nova Experimental Chat 10 20 scores higher in 8 categories and Qwen2-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Amazon Nova Experimental Chat 10 20 leads 38.5 to 21.2.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Experimental Chat 10 20 | Qwen2-72B |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 42.1 | 30.0 |
| Rank | 118 | 300 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Experimental Chat 10 20: 41.6 (#123)
- Qwen2-72B: 29.1 (#310)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1412 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Amazon Nova Experimental Chat 10 20: —
- Qwen2-72B: 17.0 (#146)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Amazon Nova Experimental Chat 10 20: 28.4 (#106)
- Qwen2-72B: 23.2 (#181)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1396 | 1191 |
| Epoch Capabilities Index | — | 125.28 |

## Math

- Amazon Nova Experimental Chat 10 20: 39.0 (#119)
- Qwen2-72B: 30.2 (#236)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1425 | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Amazon Nova Experimental Chat 10 20: 38.5 (#144)
- Qwen2-72B: 21.2 (#275)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1386 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |

## Multilingual

- Amazon Nova Experimental Chat 10 20: 49.5 (#131)
- Qwen2-72B: 35.9 (#244)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1372 | 1176 |
| LMArena Chinese | 1404 | 1240 |
| LMArena French | 1425 | 1170 |
| LMArena German | 1391 | 1151 |
| LMArena Japanese | 1360 | 1111 |
| LMArena Korean | 1324 | 1083 |
| LMArena Russian | 1371 | 1169 |
| LMArena Spanish | 1382 | 1169 |

## Instruction Following

- Amazon Nova Experimental Chat 10 20: 72.1 (#141)
- Qwen2-72B: 61.7 (#241)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1365 | 1181 |

## Long Context

- Amazon Nova Experimental Chat 10 20: 41.7 (#133)
- Qwen2-72B: 36.1 (#235)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1370 | 1192 |

## Writing & Preference

- Amazon Nova Experimental Chat 10 20: 56.6 (#136)
- Qwen2-72B: 40.8 (#241)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1394 | 1203 |
| LMArena Creative Writing | 1318 | 1181 |
| LMArena Multi-Turn | 1364 | 1196 |

## FAQ

### Is Amazon Nova Experimental Chat 10 20 better than Qwen2-72B?

Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 42.1 to 30.0 on the Noometry Index.

### Is Amazon Nova Experimental Chat 10 20 or Qwen2-72B better for coding?

Amazon Nova Experimental Chat 10 20 scores higher on coding benchmarks: 41.6 versus 29.1 in the Noometry coding category.

### How many benchmarks do Amazon Nova Experimental Chat 10 20 and Qwen2-72B share?

17 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 20 has 17 scored results on Noometry and Qwen2-72B has 26.