# Claude 3 Sonnet vs Llama 4 Scout

> Claude 3 Sonnet is the stronger model overall, scoring 28.8 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-llama-4-scout
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude 3 Sonnet scores higher in 4 categories and Llama 4 Scout in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 4 Scout leads 31.8 to 21.1.
- The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 62.3% for Llama 4 Scout.
- Llama 4 Scout has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | Llama 4 Scout |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 28.8 | 27.4 |
| Rank | 311 | 323 |
| Context | — | 128K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.30 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- Llama 4 Scout: 19.9 (#334)

| Benchmark | Claude 3 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Coding | 1223 | 1286 |
| BigCodeBench Complete | 53.8% | 43.1% |
| SWE-bench Verified (bash only) | — | 9.1% |
| SciCode | — | 17% |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- Llama 4 Scout: 24.4 (#109)

| Benchmark | Claude 3 Sonnet | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- Llama 4 Scout: 9.2 (#339)

| Benchmark | Claude 3 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1266 |
| DTBench | 53.6% | 57.9% |
| Epoch Capabilities Index | 120.69 | 129.64 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 36.9% |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| LMCA | — | 12% |
| ForecastBench | — | 57.5 |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- Llama 4 Scout: 18.4 (#280)

| Benchmark | Claude 3 Sonnet | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 7.8% |
| LMArena Math | 1213 | 1286 |
| MATH Level 5 | 18.2% | 62.3% |
| Omni-MATH | — | 37.3% |
| FrontierMath (Feb 2025 set) | — | 0% |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- Llama 4 Scout: 31.8 (#208)

| Benchmark | Claude 3 Sonnet | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 40.6% | 51.8% |
| LMArena Expert | 1173 | 1236 |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- Llama 4 Scout: 31.6 (#98)

| Benchmark | Claude 3 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 984 | 1118 |
| SpatialViz-Bench | — | 34.2% |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- Llama 4 Scout: 41.3 (#207)

| Benchmark | Claude 3 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1205 | 1253 |
| LMArena Chinese | 1188 | 1256 |
| LMArena French | 1228 | 1283 |
| LMArena German | 1204 | 1274 |
| LMArena Japanese | 1131 | 1209 |
| LMArena Korean | 1128 | 1207 |
| LMArena Russian | 1227 | 1263 |
| LMArena Spanish | 1204 | 1277 |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- Llama 4 Scout: 66.0 (#212)

| Benchmark | Claude 3 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1200 | 1248 |
| IFEval | — | 81.8% |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- Llama 4 Scout: 27.5 (#289)

| Benchmark | Claude 3 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1211 | 1265 |
| Fiction.LiveBench | — | 36% |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- Llama 4 Scout: 37.1 (#256)

| Benchmark | Claude 3 Sonnet | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1218 | 1279 |
| LMArena Creative Writing | 1186 | 1249 |
| LMArena Multi-Turn | 1227 | 1281 |
| EQ-Bench Creative Writing | — | 783 |
| WildBench | — | 78% |

## FAQ

### Is Claude 3 Sonnet better than Llama 4 Scout?

Claude 3 Sonnet is the stronger model overall, scoring 28.8 to 27.4 on the Noometry Index.

### Is Claude 3 Sonnet or Llama 4 Scout better for coding?

Claude 3 Sonnet scores higher on coding benchmarks: 29.2 versus 19.9 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and Llama 4 Scout share?

24 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Llama 4 Scout has 43.