# Claude 2 vs Llama 3.2 90B

> Llama 3.2 90B is the stronger model overall, scoring 27.5 to 25.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-llama-3-2-90b
- 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 3.2 90B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.2 90B leads 21.7 to 16.9.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for Claude 2 and 39.4% for Llama 3.2 90B.
- Llama 3.2 90B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 2 | Llama 3.2 90B |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 25.0 | 27.5 |
| Rank | 346 | 331 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 2: —
- Llama 3.2 90B: —

| Benchmark | Claude 2 | Llama 3.2 90B |
|---|---|---|
| HumanEval+ | 61.6% | — |

## Agentic & Tool Use

- Claude 2: —
- Llama 3.2 90B: 30.0 (#80)

| Benchmark | Claude 2 | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |

## Reasoning

- Claude 2: 21.7 (#216)
- Llama 3.2 90B: 21.7 (#217)

| Benchmark | Claude 2 | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 120.13 | 125.5 |
| EnigmaEval | — | 0.4% |
| DTBench | 51.9% | — |

## Math

- Claude 2: 9.3 (#320)
- Llama 3.2 90B: 11.1 (#308)

| Benchmark | Claude 2 | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 2.6% |
| MATH Level 5 | 11.7% | 39.4% |

## Knowledge

- Claude 2: 16.9 (#287)
- Llama 3.2 90B: 21.7 (#274)

| Benchmark | Claude 2 | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 34.7% | 41% |
| MMLU | 78.5% | 80.3% |
| TriviaQA | 87.5% | — |

## Multimodal

- Claude 2: —
- Llama 3.2 90B: 25.4 (#124)

| Benchmark | Claude 2 | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## FAQ

### Is Claude 2 better than Llama 3.2 90B?

Llama 3.2 90B is the stronger model overall, scoring 27.5 to 25.0 on the Noometry Index.

### How many benchmarks do Claude 2 and Llama 3.2 90B share?

5 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and Llama 3.2 90B has 9.