# Amazon Nova Experimental Chat 10 20 vs Llama 2-13B

> Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 42.1 to 29.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-experimental-chat-10-20-vs-llama-2-13b
- 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 Llama 2-13B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Experimental Chat 10 20 leads 56.6 to 29.8.
- Llama 2-13B has downloadable open weights; the other is API-only.

## Snapshot

| | Amazon Nova Experimental Chat 10 20 | Llama 2-13B |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 42.1 | 29.6 |
| Rank | 118 | 309 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Amazon Nova Experimental Chat 10 20: 41.6 (#123)
- Llama 2-13B: 30.9 (#291)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1412 | 1062 |

## Reasoning

- Amazon Nova Experimental Chat 10 20: 28.4 (#106)
- Llama 2-13B: 12.8 (#337)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1396 | 1051 |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.2% |
| BIG-Bench Hard | — | 58.2% |
| Epoch Capabilities Index | — | 106.17 |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |

## Math

- Amazon Nova Experimental Chat 10 20: 39.0 (#119)
- Llama 2-13B: 31.1 (#229)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Llama 2-13B |
|---|---|---|
| LMArena Math | 1425 | 1065 |
| GSM8K | — | 36.9% |

## Knowledge

- Amazon Nova Experimental Chat 10 20: 38.5 (#144)
- Llama 2-13B: 28.1 (#249)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1386 | 1030 |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |

## Multimodal

- Amazon Nova Experimental Chat 10 20: —
- Llama 2-13B: —

| Benchmark | Amazon Nova Experimental Chat 10 20 | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |

## Multilingual

- Amazon Nova Experimental Chat 10 20: 49.5 (#131)
- Llama 2-13B: 26.5 (#279)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1372 | 1024 |
| LMArena Chinese | 1404 | 1001 |
| LMArena French | 1425 | 1044 |
| LMArena German | 1391 | 1009 |
| LMArena Japanese | 1360 | 894 |
| LMArena Korean | 1324 | 953 |
| LMArena Russian | 1371 | 1055 |
| LMArena Spanish | 1382 | 1087 |

## Instruction Following

- Amazon Nova Experimental Chat 10 20: 72.1 (#141)
- Llama 2-13B: 53.3 (#287)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1365 | 1045 |

## Long Context

- Amazon Nova Experimental Chat 10 20: 41.7 (#133)
- Llama 2-13B: 32.3 (#269)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1370 | 1064 |

## Writing & Preference

- Amazon Nova Experimental Chat 10 20: 56.6 (#136)
- Llama 2-13B: 29.8 (#289)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Llama 2-13B |
|---|---|---|
| LMArena Text | 1394 | 1084 |
| LMArena Creative Writing | 1318 | 1047 |
| LMArena Multi-Turn | 1364 | 1050 |

## FAQ

### Is Amazon Nova Experimental Chat 10 20 better than Llama 2-13B?

Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 42.1 to 29.6 on the Noometry Index.

### Is Amazon Nova Experimental Chat 10 20 or Llama 2-13B better for coding?

Amazon Nova Experimental Chat 10 20 scores higher on coding benchmarks: 41.6 versus 30.9 in the Noometry coding category.

### How many benchmarks do Amazon Nova Experimental Chat 10 20 and Llama 2-13B share?

17 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 20 has 17 scored results on Noometry and Llama 2-13B has 32.