Meta, open weights

# Llama 3.2 90B

> Llama 3.2 90B by Meta, released September 2024. Ranked #331 of 354 with a Noometry Index of 27.5. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/llama-3-2-90b
- Last updated: 2026-10-10
- Title: Llama 3.2 90B Benchmarks, Price & Rank (October 2026)

Llama 3.2 90B by Meta ranks 331st of 354 ranked models on the Noometry Index as of October 2026, with a score of 27.5. Its strongest category is agentic & tool use, where it ranks 80th.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #331 of 354
- **Index score:** 27.5
- **Evidence:** Confirmed 9 results
- **Provider:** [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta)
- **Released:** September 24, 2024
- **Weights:** Open weights
- **Reasoning:** Unknown
- **Context window:** —
- **Max output:** —
- **Input price:** Not listed
- **Output price:** Not listed
- **Blended price:** Not listed
- **Output speed:** Not measured
- **Value:** Not ranked
- **Knowledge cutoff:** Unknown

## Category scores

Each category score combines every public result we have in that category.

Llama 3.2 90B category scores

1.  Agentic & Tool Use 30.0
2.  Reasoning 21.7
3.  Math 11.1
4.  Knowledge 21.7
5.  Multimodal 25.4
6.  010203040

Llama 3.2 90B category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 30.0 | #80 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 21.7 | #217 | 1 |
| [Math](https://noometry.com/best/math) | 11.1 | #308 | 2 |
| [Knowledge](https://noometry.com/best/knowledge) | 21.7 | #274 | 1 |
| [Multimodal](https://noometry.com/best/multimodal) | 25.4 | #124 | 2 |

## Strengths and weaknesses

Categories where Llama 3.2 90B places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Llama 3.2 90B: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 30.0 | −0.3 | #80 of 154, top 52% |
| [Reasoning](https://noometry.com/best/reasoning) | 21.7 | −1.9 | #217 of 350, top 62% |

### Weakest categories

Llama 3.2 90B: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Multimodal](https://noometry.com/best/multimodal) | 25.4 | −13.1 | #124 of 128, top 97% |
| [Math](https://noometry.com/best/math) | 11.1 | −25.5 | #308 of 327, top 95% |

## Closest competitors

The models ranked just above and below Llama 3.2 90B. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Llama 3.2 90B
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [GPT-4.1 nano](https://noometry.com/models/gpt-4-1-nano) | #327 | 27.9 | $0.18 | 135 | [Compare](https://noometry.com/compare/gpt-4-1-nano-vs-llama-3-2-90b) |
| [Phi 3 Mini 4k Instruct](https://noometry.com/models/phi-3-mini-4k-instruct) | #328 | 27.9 | — | — | [Compare](https://noometry.com/compare/llama-3-2-90b-vs-phi-3-mini-4k-instruct) |
| [Yi-34B](https://noometry.com/models/yi-34b) | #329 | 27.8 | — | — | [Compare](https://noometry.com/compare/llama-3-2-90b-vs-yi-34b) |
| [Llama 4 Scout](https://noometry.com/models/llama-4-scout) | #330 | 27.7 | $0.15 | 272 | [Compare](https://noometry.com/compare/llama-3-2-90b-vs-llama-4-scout) |
| [Gemini 1.0 Pro](https://noometry.com/models/gemini-1-0-pro) | #332 | 27.3 | — | — | [Compare](https://noometry.com/compare/gemini-1-0-pro-vs-llama-3-2-90b) |
| [Mixtral 8x22B](https://noometry.com/models/mixtral-8x22b) | #333 | 27.1 | $3 | — | [Compare](https://noometry.com/compare/llama-3-2-90b-vs-mixtral-8x22b) |
| [Mixtral 8x7B](https://noometry.com/models/mixtral-8x7b) | #334 | 27.1 | $0.70 | — | [Compare](https://noometry.com/compare/llama-3-2-90b-vs-mixtral-8x7b) |
| [Qwen Turbo](https://noometry.com/models/qwen-turbo) | #335 | 27.1 | $0.0875 | — | [Compare](https://noometry.com/compare/llama-3-2-90b-vs-qwen-turbo) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Agentic & Tool Use

Llama 3.2 90B Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [BALROG](https://noometry.com/benchmarks/balrog) | 27.3% | #21 of 35, top 60% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

Llama 3.2 90B Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [EnigmaEval](https://noometry.com/benchmarks/enigmaeval) | 0.4% | #38 of 38, top 100% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 125.5 | #156 of 213, top 74% |  | [Epoch AI](https://epoch.ai/eci) | 2024-09-24 |

### Math

Llama 3.2 90B Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 2.6% | #156 of 173, top 91% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-02-25 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 39.4% | #52 of 79, top 66% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |

### Knowledge

Llama 3.2 90B Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 41% | #147 of 186, top 80% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |
| [MMLU](https://noometry.com/benchmarks/mmlu) | 80.3% | #15 of 81, top 19% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Multimodal

Llama 3.2 90B Multimodal benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Vision](https://noometry.com/benchmarks/arena-vision) | 1000 | #117 of 122, top 96% |  | [LMArena](https://lmarena.ai/leaderboard/vision) | 2026-10-09 |
| [GeoBench](https://noometry.com/benchmarks/geobench) | 52% | #19 of 25, top 76% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## Compare Llama 3.2 90B

-   [Llama 3.2 90B vs Llama 3.1-405B](https://noometry.com/compare/llama-3-1-405b-vs-llama-3-2-90b)
-   [Llama 3.2 90B vs Llama 4 Scout](https://noometry.com/compare/llama-3-2-90b-vs-llama-4-scout)
-   [Llama 3.2 90B vs Gemini 1.0 Pro](https://noometry.com/compare/gemini-1-0-pro-vs-llama-3-2-90b)
-   [Llama 3.2 90B vs Yi-34B](https://noometry.com/compare/llama-3-2-90b-vs-yi-34b)
-   [Llama 3.2 90B vs Mixtral 8x22B](https://noometry.com/compare/llama-3-2-90b-vs-mixtral-8x22b)
-   [Llama 3.2 90B vs Phi 3 Mini 4k Instruct](https://noometry.com/compare/llama-3-2-90b-vs-phi-3-mini-4k-instruct)
-   [Llama 3.2 90B vs Mixtral 8x7B](https://noometry.com/compare/llama-3-2-90b-vs-mixtral-8x7b)
-   [Llama 3.2 90B vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-llama-3-2-90b)
-   [Llama 3.2 90B vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-llama-3-2-90b)
-   [Llama 3.2 90B vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-llama-3-2-90b)
-   [Llama 3.2 90B vs Kimi K3](https://noometry.com/compare/kimi-k3-vs-llama-3-2-90b)
-   [Llama 3.2 90B vs Grok 4.6](https://noometry.com/compare/grok-4-6-vs-llama-3-2-90b)
-   [Llama 3.2 90B vs Qwen3.8 Max](https://noometry.com/compare/llama-3-2-90b-vs-qwen3-8-max)
-   [Llama 3.2 90B vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-llama-3-2-90b)

## Other Meta models

-   [Muse Spark 1.3](https://noometry.com/models/muse-spark-1-3)54.8
-   [Muse Spark](https://noometry.com/models/muse-spark)50.6
-   [Muse Spark 1.2](https://noometry.com/models/muse-spark-1-2)50.3
-   [Muse Spark 1.1](https://noometry.com/models/muse-spark-1-1)49.9
-   [Muse Glimmer](https://noometry.com/models/muse-glimmer)41.7
-   [Codellama 70b Instruct](https://noometry.com/models/codellama-70b-instruct)33.7
-   [Llama 4 Maverick](https://noometry.com/models/llama-4-maverick)30.9
-   [Codellama 34b Instruct](https://noometry.com/models/codellama-34b-instruct)30.8

## Frequently asked questions

### How good is Llama 3.2 90B?

Llama 3.2 90B by Meta ranks 331st of 354 ranked models on the Noometry Index as of October 2026, with a score of 27.5. Its strongest category is agentic & tool use, where it ranks 80th.

### Is Llama 3.2 90B open source?

Yes. Llama 3.2 90B's weights are downloadable; check the license for commercial terms.

### What are Llama 3.2 90B's strengths and weaknesses?

Relative to other ranked models, Llama 3.2 90B places best in agentic & tool use, reasoning and lowest in multimodal, math.

### What is Llama 3.2 90B best at?

Its best category is agentic & tool use, where it ranks 80th on Noometry.

### Cite this page

Noometry. (2026). Llama 3.2 90B benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/llama-3-2-90b

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/llama-3-2-90b.md).