# Claude Sonnet 4 vs Llama 3.1-405B

> Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 30.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-vs-llama-3-1-405b
- Last updated: 2026-10-10
- Shared benchmarks: 35

## Summary

- They share 35 benchmarks with published results for both. Claude Sonnet 4 scores higher in 8 categories and Llama 3.1-405B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4 leads 43.3 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 9.7% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 4 | Llama 3.1-405B |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 40.8 | 30.7 |
| Rank | 145 | 288 |
| Context | 200K | — |
| Input $/M | $3 | — |
| Output $/M | $15 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 4: 43.5 (#88)
- Llama 3.1-405B: 33.1 (#262)

| Benchmark | Claude Sonnet 4 | Llama 3.1-405B |
|---|---|---|
| WeirdML | 46.1% | 21.4% |
| LMArena Coding | 1414 | 1291 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| ALE-Bench | 655.35 | — |

## Agentic & Tool Use

- Claude Sonnet 4: 38.5 (#31)
- Llama 3.1-405B: 21.0 (#140)

| Benchmark | Claude Sonnet 4 | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | 33.1% | 7.4% |
| Cybench | 35% | 7.5% |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |

## Reasoning

- Claude Sonnet 4: 22.9 (#187)
- Llama 3.1-405B: 16.8 (#300)

| Benchmark | Claude Sonnet 4 | Llama 3.1-405B |
|---|---|---|
| SimpleBench | 45.5% | 23% |
| Kagi LLM Benchmark | 73% | 45% |
| LMArena Hard Prompts | 1372 | 1269 |
| DTBench | 77.1% | 61.4% |
| Epoch Capabilities Index | 141.69 | 128.75 |
| ForecastBench | 60.2 | 59.9 |
| ARC-AGI-2 | 5.9% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| LMCA | 29% | — |
| BIG-Bench Hard | — | 82.9% |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |

## Math

- Claude Sonnet 4: 43.3 (#80)
- Llama 3.1-405B: 18.4 (#290)

| Benchmark | Claude Sonnet 4 | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 9.7% |
| Omni-MATH | 60.2% | 24.9% |
| LMArena Math | 1375 | 1281 |
| MATH Level 5 | 84.4% | 49.8% |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Claude Sonnet 4: 41.8 (#108)
- Llama 3.1-405B: 30.4 (#227)

| Benchmark | Claude Sonnet 4 | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 79.2% | 50.9% |
| MMLU-Pro | 84.3% | 72.3% |
| Confabulations | 13.2% | 17.6% |
| GPQA (HELM) | 70.6% | 52.2% |
| LMArena Expert | 1372 | 1243 |
| Humanity's Last Exam | 7.8% | — |
| Vectara Hallucination Rate | 10.3% | — |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |

## Multimodal

- Claude Sonnet 4: 26.2 (#121)
- Llama 3.1-405B: —

| Benchmark | Claude Sonnet 4 | Llama 3.1-405B |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |

## Multilingual

- Claude Sonnet 4: 46.7 (#156)
- Llama 3.1-405B: 40.7 (#214)

| Benchmark | Claude Sonnet 4 | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1333 | 1248 |
| LMArena Chinese | 1350 | 1242 |
| LMArena French | 1363 | 1279 |
| LMArena German | 1331 | 1252 |
| LMArena Japanese | 1302 | 1208 |
| LMArena Korean | 1291 | 1184 |
| LMArena Russian | 1355 | 1265 |
| LMArena Spanish | 1357 | 1260 |

## Instruction Following

- Claude Sonnet 4: 71.7 (#145)
- Llama 3.1-405B: 65.9 (#214)

| Benchmark | Claude Sonnet 4 | Llama 3.1-405B |
|---|---|---|
| IFEval | 84% | 81.1% |
| LMArena Instruction Following | 1376 | 1259 |

## Long Context

- Claude Sonnet 4: 33.7 (#259)
- Llama 3.1-405B: 38.4 (#197)

| Benchmark | Claude Sonnet 4 | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1398 | 1266 |
| Fiction.LiveBench | 46.9% | — |

## Writing & Preference

- Claude Sonnet 4: 57.1 (#132)
- Llama 3.1-405B: 38.9 (#251)

| Benchmark | Claude Sonnet 4 | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1351 | 1284 |
| LMArena Creative Writing | 1345 | 1262 |
| EQ-Bench Creative Writing | 1483 | 870 |
| WildBench | 83.8% | 78.3% |
| LMArena Multi-Turn | 1376 | 1297 |
| Short-Story Creative Writing | 81.4% | — |

## FAQ

### Is Claude Sonnet 4 better than Llama 3.1-405B?

Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 30.7 on the Noometry Index.

### Is Claude Sonnet 4 or Llama 3.1-405B better for coding?

Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 33.1 in the Noometry coding category.

### How many benchmarks do Claude Sonnet 4 and Llama 3.1-405B share?

35 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Llama 3.1-405B has 42.