# Claude 2 vs Llama 2-70B

> Claude 2 and Llama 2-70B score almost the same on the Noometry Index (25.0 vs 24.4), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/claude-2-vs-llama-2-70b
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. Claude 2 scores higher in 3 categories and Llama 2-70B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude 2 leads 16.9 to 7.4.
- The biggest single-benchmark swing is DTBench: 51.9% for Claude 2 and 41.6% for Llama 2-70B.
- Llama 2-70B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2 | Llama 2-70B |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 25.0 | 24.4 |
| Rank | 346 | 349 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 2: —
- Llama 2-70B: 31.4 (#286)

| Benchmark | Claude 2 | Llama 2-70B |
|---|---|---|
| LMArena Coding | — | 1079 |
| HumanEval+ | 61.6% | — |

## Reasoning

- Claude 2: 21.7 (#216)
- Llama 2-70B: 14.4 (#325)

| Benchmark | Claude 2 | Llama 2-70B |
|---|---|---|
| DTBench | 51.9% | 41.6% |
| Epoch Capabilities Index | 120.13 | 113.79 |
| LMArena Hard Prompts | — | 1073 |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |

## Math

- Claude 2: 9.3 (#320)
- Llama 2-70B: 8.1 (#326)

| Benchmark | Claude 2 | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 0% |
| MATH Level 5 | 11.7% | 3.3% |
| LMArena Math | — | 1091 |
| GSM8K | — | 69.6% |

## Knowledge

- Claude 2: 16.9 (#287)
- Llama 2-70B: 7.4 (#310)

| Benchmark | Claude 2 | Llama 2-70B |
|---|---|---|
| GPQA Diamond | 34.7% | 26.3% |
| MMLU | 78.5% | 69.9% |
| TriviaQA | 87.5% | 87.6% |
| LMArena Expert | — | 1039 |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| OpenBookQA | — | 60.2% |

## Multilingual

- Claude 2: —
- Llama 2-70B: 27.7 (#274)

| Benchmark | Claude 2 | Llama 2-70B |
|---|---|---|
| LMArena Non-English | — | 1045 |
| LMArena Chinese | — | 995 |
| LMArena French | — | 1090 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Russian | — | 1083 |
| LMArena Spanish | — | 1143 |

## Instruction Following

- Claude 2: —
- Llama 2-70B: 54.9 (#278)

| Benchmark | Claude 2 | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | — | 1071 |

## Long Context

- Claude 2: —
- Llama 2-70B: 32.3 (#270)

| Benchmark | Claude 2 | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | — | 1062 |

## Writing & Preference

- Claude 2: —
- Llama 2-70B: 32.3 (#279)

| Benchmark | Claude 2 | Llama 2-70B |
|---|---|---|
| LMArena Text | — | 1115 |
| LMArena Creative Writing | — | 1075 |
| LMArena Multi-Turn | — | 1088 |

## FAQ

### Is Claude 2 better than Llama 2-70B?

Claude 2 and Llama 2-70B score almost the same on the Noometry Index (25.0 vs 24.4), so choose on price, context window or the category you care about most.

### How many benchmarks do Claude 2 and Llama 2-70B share?

7 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Llama 2-70B has 35.