# Claude 2 vs Llama 3.1-405B

> Llama 3.1-405B is the stronger model overall, scoring 30.7 to 25.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-llama-3-1-405b
- Last updated: 2026-10-12
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. Claude 2 scores higher in 1 category and Llama 3.1-405B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.1-405B leads 30.4 to 16.9.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for Claude 2 and 49.8% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2 | Llama 3.1-405B |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 25.0 | 30.7 |
| Rank | 346 | 288 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 2: —
- Llama 3.1-405B: 33.1 (#262)

| Benchmark | Claude 2 | Llama 3.1-405B |
|---|---|---|
| WeirdML | — | 21.4% |
| LMArena Coding | — | 1291 |
| HumanEval+ | 61.6% | — |

## Agentic & Tool Use

- Claude 2: —
- Llama 3.1-405B: 21.0 (#140)

| Benchmark | Claude 2 | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |

## Reasoning

- Claude 2: 21.7 (#216)
- Llama 3.1-405B: 16.8 (#300)

| Benchmark | Claude 2 | Llama 3.1-405B |
|---|---|---|
| DTBench | 51.9% | 61.4% |
| Epoch Capabilities Index | 120.13 | 128.75 |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| LMArena Hard Prompts | — | 1269 |
| BIG-Bench Hard | — | 82.9% |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |

## Math

- Claude 2: 9.3 (#320)
- Llama 3.1-405B: 18.4 (#290)

| Benchmark | Claude 2 | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 9.7% |
| MATH Level 5 | 11.7% | 49.8% |
| Omni-MATH | — | 24.9% |
| LMArena Math | — | 1281 |

## Knowledge

- Claude 2: 16.9 (#287)
- Llama 3.1-405B: 30.4 (#227)

| Benchmark | Claude 2 | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 34.7% | 50.9% |
| MMLU | 78.5% | 84.5% |
| TriviaQA | 87.5% | 82.7% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| LMArena Expert | — | 1243 |
| ARC (AI2) Challenge | — | 95.3% |

## Multilingual

- Claude 2: —
- Llama 3.1-405B: 40.7 (#214)

| Benchmark | Claude 2 | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | — | 1248 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1279 |
| LMArena German | — | 1252 |
| LMArena Japanese | — | 1208 |
| LMArena Korean | — | 1184 |
| LMArena Russian | — | 1265 |
| LMArena Spanish | — | 1260 |

## Instruction Following

- Claude 2: —
- Llama 3.1-405B: 65.9 (#214)

| Benchmark | Claude 2 | Llama 3.1-405B |
|---|---|---|
| IFEval | — | 81.1% |
| LMArena Instruction Following | — | 1259 |

## Long Context

- Claude 2: —
- Llama 3.1-405B: 38.4 (#197)

| Benchmark | Claude 2 | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | — | 1266 |

## Writing & Preference

- Claude 2: —
- Llama 3.1-405B: 38.9 (#251)

| Benchmark | Claude 2 | Llama 3.1-405B |
|---|---|---|
| LMArena Text | — | 1284 |
| LMArena Creative Writing | — | 1262 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
| LMArena Multi-Turn | — | 1297 |

## FAQ

### Is Claude 2 better than Llama 3.1-405B?

Llama 3.1-405B is the stronger model overall, scoring 30.7 to 25.0 on the Noometry Index.

### How many benchmarks do Claude 2 and Llama 3.1-405B share?

7 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Llama 3.1-405B has 42.