# Claude 2 vs Llama 4 Scout

> Llama 4 Scout is the stronger model overall, scoring 27.7 to 25.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-llama-4-scout
- Last updated: 2026-10-11
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. Claude 2 scores higher in 1 category and Llama 4 Scout in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 4 Scout leads 31.9 to 16.9.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for Claude 2 and 62.3% for Llama 4 Scout.
- Llama 4 Scout has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2 | Llama 4 Scout |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 25.0 | 27.7 |
| Rank | 346 | 330 |
| Context | — | 128K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.30 |
| Weights | Proprietary | Open |

## Coding

- Claude 2: —
- Llama 4 Scout: 20.2 (#339)

| Benchmark | Claude 2 | Llama 4 Scout |
|---|---|---|
| SWE-bench Verified (bash only) | — | 9.1% |
| SciCode | — | 17% |
| LMArena Coding | — | 1286 |
| BigCodeBench Complete | — | 43.1% |
| HumanEval+ | 61.6% | — |

## Agentic & Tool Use

- Claude 2: —
- Llama 4 Scout: 24.6 (#119)

| Benchmark | Claude 2 | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |

## Reasoning

- Claude 2: 21.7 (#216)
- Llama 4 Scout: 9.1 (#345)

| Benchmark | Claude 2 | Llama 4 Scout |
|---|---|---|
| DTBench | 51.9% | 57.9% |
| Epoch Capabilities Index | 120.13 | 129.64 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 36.9% |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| LMArena Hard Prompts | — | 1266 |
| LMCA | — | 12% |
| ForecastBench | — | 57.5 |

## Math

- Claude 2: 9.3 (#320)
- Llama 4 Scout: 19.6 (#286)

| Benchmark | Claude 2 | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 7.8% |
| MATH Level 5 | 11.7% | 62.3% |
| Omni-MATH | — | 37.3% |
| LMArena Math | — | 1287 |
| FrontierMath (Feb 2025 set) | — | 0% |

## Knowledge

- Claude 2: 16.9 (#287)
- Llama 4 Scout: 31.9 (#217)

| Benchmark | Claude 2 | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 34.7% | 51.8% |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
| LMArena Expert | — | 1235 |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |

## Multimodal

- Claude 2: —
- Llama 4 Scout: 32.2 (#102)

| Benchmark | Claude 2 | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |

## Multilingual

- Claude 2: —
- Llama 4 Scout: 41.0 (#212)

| Benchmark | Claude 2 | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | — | 1252 |
| LMArena Chinese | — | 1255 |
| LMArena French | — | 1282 |
| LMArena German | — | 1272 |
| LMArena Japanese | — | 1206 |
| LMArena Korean | — | 1207 |
| LMArena Russian | — | 1263 |
| LMArena Spanish | — | 1278 |

## Instruction Following

- Claude 2: —
- Llama 4 Scout: 65.8 (#217)

| Benchmark | Claude 2 | Llama 4 Scout |
|---|---|---|
| IFEval | — | 81.8% |
| LMArena Instruction Following | — | 1248 |

## Long Context

- Claude 2: —
- Llama 4 Scout: 27.5 (#294)

| Benchmark | Claude 2 | Llama 4 Scout |
|---|---|---|
| Fiction.LiveBench | — | 36% |
| LMArena Longer Query | — | 1265 |

## Writing & Preference

- Claude 2: —
- Llama 4 Scout: 37.0 (#261)

| Benchmark | Claude 2 | Llama 4 Scout |
|---|---|---|
| LMArena Text | — | 1279 |
| LMArena Creative Writing | — | 1249 |
| EQ-Bench Creative Writing | — | 783 |
| WildBench | — | 78% |
| LMArena Multi-Turn | — | 1280 |

## FAQ

### Is Claude 2 better than Llama 4 Scout?

Llama 4 Scout is the stronger model overall, scoring 27.7 to 25.0 on the Noometry Index.

### How many benchmarks do Claude 2 and Llama 4 Scout share?

5 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Llama 4 Scout has 43.