# Amazon Nova Experimental Chat 10 20 vs Claude 3.5 Sonnet

> Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 42.1 to 34.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-experimental-chat-10-20-vs-claude-3-5-sonnet
- 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 Claude 3.5 Sonnet in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Experimental Chat 10 20 leads 39.0 to 19.2.

## Snapshot

| | Amazon Nova Experimental Chat 10 20 | Claude 3.5 Sonnet |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 42.1 | 34.6 |
| Rank | 118 | 231 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Experimental Chat 10 20: 41.6 (#123)
- Claude 3.5 Sonnet: 39.0 (#165)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Coding | 1412 | 1342 |
| Aider Polyglot | — | 51.6% |
| GSO | — | 4.6% |
| WeirdML | — | 40% |
| BigCodeBench Instruct | — | 46.8% |
| LiveBench Coding | — | 67.1% |
| BigCodeBench Complete | — | 58.6% |
| CadEval | — | 48% |
| HumanEval+ | — | 81.7% |
| MBPP+ | — | 74.3% |

## Agentic & Tool Use

- Amazon Nova Experimental Chat 10 20: —
- Claude 3.5 Sonnet: 32.3 (#67)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Claude 3.5 Sonnet |
|---|---|---|
| TheAgentCompany | — | 24% |
| Cybench | — | 17.5% |
| BALROG | — | 32.6% |
| METR Time Horizons | — | 45.2% |

## Reasoning

- Amazon Nova Experimental Chat 10 20: 28.4 (#106)
- Claude 3.5 Sonnet: 23.1 (#183)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Hard Prompts | 1396 | 1305 |
| SimpleBench | — | 41.4% |
| EnigmaEval | — | 0.9% |
| LiveBench Reasoning | — | 56.7% |
| DTBench | — | 67.8% |
| LiveBench Data Analysis | — | 55% |
| Epoch Capabilities Index | — | 133.55 |
| ForecastBench | — | 60.7 |
| LiveBench | — | 59% |

## Math

- Amazon Nova Experimental Chat 10 20: 39.0 (#119)
- Claude 3.5 Sonnet: 19.2 (#288)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Math | 1425 | 1307 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| Omni-MATH | — | 27.6% |
| LiveBench Math | — | 52.3% |
| MATH Level 5 | — | 56.9% |
| FrontierMath (Feb 2025 set) | — | 2.1% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Amazon Nova Experimental Chat 10 20: 38.5 (#144)
- Claude 3.5 Sonnet: 28.6 (#245)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Expert | 1386 | 1265 |
| GPQA Diamond | — | 55.3% |
| Humanity's Last Exam | — | 4.1% |
| MMLU-Pro | — | 77.7% |
| Confabulations | — | 19.9% |
| GPQA (HELM) | — | 56.5% |
| MMLU | — | 87.3% |

## Multimodal

- Amazon Nova Experimental Chat 10 20: —
- Claude 3.5 Sonnet: 26.5 (#120)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Vision | — | 1125 |
| Video-MME | — | 60% |
| GeoBench | — | 62% |
| VPCT | — | 33% |

## Multilingual

- Amazon Nova Experimental Chat 10 20: 49.5 (#131)
- Claude 3.5 Sonnet: 43.2 (#185)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Non-English | 1372 | 1283 |
| LMArena Chinese | 1404 | 1272 |
| LMArena French | 1425 | 1305 |
| LMArena German | 1391 | 1297 |
| LMArena Japanese | 1360 | 1234 |
| LMArena Korean | 1324 | 1200 |
| LMArena Russian | 1371 | 1306 |
| LMArena Spanish | 1382 | 1290 |

## Instruction Following

- Amazon Nova Experimental Chat 10 20: 72.1 (#141)
- Claude 3.5 Sonnet: 68.8 (#182)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Instruction Following | 1365 | 1297 |
| LiveBench Instruction Following | — | 69.3% |
| IFEval | — | 85.5% |

## Long Context

- Amazon Nova Experimental Chat 10 20: 41.7 (#133)
- Claude 3.5 Sonnet: 39.9 (#167)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Longer Query | 1370 | 1311 |

## Writing & Preference

- Amazon Nova Experimental Chat 10 20: 56.6 (#136)
- Claude 3.5 Sonnet: 52.9 (#164)

| Benchmark | Amazon Nova Experimental Chat 10 20 | Claude 3.5 Sonnet |
|---|---|---|
| LMArena Text | 1394 | 1298 |
| LMArena Creative Writing | 1318 | 1292 |
| LMArena Multi-Turn | 1364 | 1326 |
| Short-Story Creative Writing | — | 80.3% |
| EQ-Bench Creative Writing | — | 1451 |
| WildBench | — | 79.2% |
| LiveBench Language | — | 53.8% |

## FAQ

### Is Amazon Nova Experimental Chat 10 20 better than Claude 3.5 Sonnet?

Amazon Nova Experimental Chat 10 20 is the stronger model overall, scoring 42.1 to 34.6 on the Noometry Index.

### Is Amazon Nova Experimental Chat 10 20 or Claude 3.5 Sonnet better for coding?

Amazon Nova Experimental Chat 10 20 scores higher on coding benchmarks: 41.6 versus 39.0 in the Noometry coding category.

### How many benchmarks do Amazon Nova Experimental Chat 10 20 and Claude 3.5 Sonnet share?

17 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 20 has 17 scored results on Noometry and Claude 3.5 Sonnet has 60.