# Amazon Nova Experimental Chat 12 10 vs Claude Sonnet 4

> Amazon Nova Experimental Chat 12 10 is the stronger model overall, scoring 42.9 to 40.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-experimental-chat-12-10-vs-claude-sonnet-4
- Last updated: 2026-10-12
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Amazon Nova Experimental Chat 12 10 scores higher in 5 categories and Claude Sonnet 4 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Amazon Nova Experimental Chat 12 10 leads 42.4 to 33.7.

## Snapshot

| | Amazon Nova Experimental Chat 12 10 | Claude Sonnet 4 |
|---|---|---|
| Provider | Amazon | Anthropic |
| Noometry Index | 42.9 | 40.8 |
| Rank | 104 | 145 |
| Context | — | 200K |
| Input $/M | — | $3 |
| Output $/M | — | $15 |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Experimental Chat 12 10: 42.2 (#110)
- Claude Sonnet 4: 43.5 (#88)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Claude Sonnet 4 |
|---|---|---|
| LMArena Coding | 1430 | 1414 |
| SWE-bench Verified (bash only) | — | 64.9% |
| Aider Polyglot | — | 61.3% |
| SciCode | — | 40% |
| GSO | — | 4.9% |
| WeirdML | — | 46.1% |
| ALE-Bench | — | 655.35 |

## Agentic & Tool Use

- Amazon Nova Experimental Chat 12 10: —
- Claude Sonnet 4: 38.5 (#31)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Claude Sonnet 4 |
|---|---|---|
| TheAgentCompany | — | 33.1% |
| Cybench | — | 35% |
| DeepResearch Bench | — | 46.6% |
| OSWorld | — | 43.9% |
| METR Time Horizons | — | 62% |

## Reasoning

- Amazon Nova Experimental Chat 12 10: 29.3 (#94)
- Claude Sonnet 4: 22.9 (#187)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Claude Sonnet 4 |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1372 |
| ARC-AGI-2 | — | 5.9% |
| SimpleBench | — | 45.5% |
| Kagi LLM Benchmark | — | 73% |
| ARC-AGI-1 | — | 40% |
| CritPt | — | 0.3% |
| EnigmaEval | — | 3.1% |
| DTBench | — | 77.1% |
| LMCA | — | 29% |
| Epoch Capabilities Index | — | 141.69 |
| ForecastBench | — | 60.2 |

## Math

- Amazon Nova Experimental Chat 12 10: 38.9 (#124)
- Claude Sonnet 4: 43.3 (#80)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Claude Sonnet 4 |
|---|---|---|
| LMArena Math | 1419 | 1375 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| Omni-MATH | — | 60.2% |
| MATH Level 5 | — | 84.4% |
| FrontierMath (Feb 2025 set) | — | 4.1% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Amazon Nova Experimental Chat 12 10: 39.2 (#136)
- Claude Sonnet 4: 41.8 (#108)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Claude Sonnet 4 |
|---|---|---|
| LMArena Expert | 1408 | 1372 |
| GPQA Diamond | — | 79.2% |
| Humanity's Last Exam | — | 7.8% |
| MMLU-Pro | — | 84.3% |
| Confabulations | — | 13.2% |
| Vectara Hallucination Rate | — | 10.3% |
| GPQA (HELM) | — | 70.6% |

## Multimodal

- Amazon Nova Experimental Chat 12 10: —
- Claude Sonnet 4: 26.2 (#121)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Claude Sonnet 4 |
|---|---|---|
| LMArena Vision | — | 1191 |
| GeoBench | — | 37% |
| VPCT | — | 34% |
| MindCube | — | 44.8% |

## Multilingual

- Amazon Nova Experimental Chat 12 10: 51.4 (#108)
- Claude Sonnet 4: 46.7 (#156)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Claude Sonnet 4 |
|---|---|---|
| LMArena Non-English | 1398 | 1333 |
| LMArena Chinese | 1440 | 1350 |
| LMArena Russian | 1395 | 1355 |
| LMArena French | — | 1363 |
| LMArena German | — | 1331 |
| LMArena Japanese | — | 1302 |
| LMArena Korean | — | 1291 |
| LMArena Spanish | — | 1357 |

## Instruction Following

- Amazon Nova Experimental Chat 12 10: 73.2 (#123)
- Claude Sonnet 4: 71.7 (#145)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Claude Sonnet 4 |
|---|---|---|
| LMArena Instruction Following | 1387 | 1376 |
| IFEval | — | 84% |

## Long Context

- Amazon Nova Experimental Chat 12 10: 42.4 (#125)
- Claude Sonnet 4: 33.7 (#259)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Claude Sonnet 4 |
|---|---|---|
| LMArena Longer Query | 1391 | 1398 |
| Fiction.LiveBench | — | 46.9% |

## Writing & Preference

- Amazon Nova Experimental Chat 12 10: 59.5 (#110)
- Claude Sonnet 4: 57.1 (#132)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Claude Sonnet 4 |
|---|---|---|
| LMArena Text | 1420 | 1351 |
| LMArena Creative Writing | 1350 | 1345 |
| LMArena Multi-Turn | 1409 | 1376 |
| Short-Story Creative Writing | — | 81.4% |
| EQ-Bench Creative Writing | — | 1483 |
| WildBench | — | 83.8% |

## FAQ

### Is Amazon Nova Experimental Chat 12 10 better than Claude Sonnet 4?

Amazon Nova Experimental Chat 12 10 is the stronger model overall, scoring 42.9 to 40.8 on the Noometry Index.

### Is Amazon Nova Experimental Chat 12 10 or Claude Sonnet 4 better for coding?

Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 42.2 in the Noometry coding category.

### How many benchmarks do Amazon Nova Experimental Chat 12 10 and Claude Sonnet 4 share?

12 benchmarks have published results for both models. Amazon Nova Experimental Chat 12 10 has 12 scored results on Noometry and Claude Sonnet 4 has 58.