Meta, open weights
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.
Last verified
Specifications
- Noometry rank
- #331 of 354
- Index score
- 27.5
- Evidence
- Confirmed 9 results
- Provider
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.
- Agentic & Tool Use 30.0
- Reasoning 21.7
- Math 11.1
- Knowledge 21.7
- Multimodal 25.4
| Category | Score | Rank | Results |
|---|---|---|---|
| Agentic & Tool Use | 30.0 | #80 | 1 |
| Reasoning | 21.7 | #217 | 1 |
| Math | 11.1 | #308 | 2 |
| Knowledge | 21.7 | #274 | 1 |
| 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
| Category | Score | vs median | Rank |
|---|---|---|---|
| Agentic & Tool Use | 30.0 | −0.3 | #80 of 154, top 52% |
| Reasoning | 21.7 | −1.9 | #217 of 350, top 62% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Multimodal | 25.4 | −13.1 | #124 of 128, top 97% |
| 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.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| GPT-4.1 nano | #327 | 27.9 | $0.18 | 135 | Compare |
| Phi 3 Mini 4k Instruct | #328 | 27.9 | — | — | Compare |
| Yi-34B | #329 | 27.8 | — | — | Compare |
| Llama 4 Scout | #330 | 27.7 | $0.15 | 272 | Compare |
| Gemini 1.0 Pro | #332 | 27.3 | — | — | Compare |
| Mixtral 8x22B | #333 | 27.1 | $3 | — | Compare |
| Mixtral 8x7B | #334 | 27.1 | $0.70 | — | Compare |
| Qwen Turbo | #335 | 27.1 | $0.0875 | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
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
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| BALROG | 27.3% | #21 of 35, top 60% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| EnigmaEval | 0.4% | #38 of 38, top 100% | Epoch AI | ||
| Epoch Capabilities Index | 125.5 | #156 of 213, top 74% | Epoch AI | 2024-09-24 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | #156 of 173, top 91% | Epoch AI | 2025-02-25 | |
| MATH Level 5 | 39.4% | #52 of 79, top 66% | Epoch AI | 2025-01-27 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 41% | #147 of 186, top 80% | Epoch AI | 2025-01-27 | |
| MMLU | 80.3% | #15 of 81, top 19% | Epoch AI |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 1000 | #117 of 122, top 96% | LMArena | 2026-10-09 | |
| GeoBench | 52% | #19 of 25, top 76% | Epoch AI |
Compare Llama 3.2 90B
- Llama 3.2 90B vs Llama 3.1-405B
- Llama 3.2 90B vs Llama 4 Scout
- Llama 3.2 90B vs Gemini 1.0 Pro
- Llama 3.2 90B vs Yi-34B
- Llama 3.2 90B vs Mixtral 8x22B
- Llama 3.2 90B vs Phi 3 Mini 4k Instruct
- Llama 3.2 90B vs Mixtral 8x7B
- Llama 3.2 90B vs GPT-6 Astra
- Llama 3.2 90B vs Claude Fable 5.1
- Llama 3.2 90B vs Gemini 3.8 Flash
- Llama 3.2 90B vs Kimi K3
- Llama 3.2 90B vs Grok 4.6
- Llama 3.2 90B vs Qwen3.8 Max
- Llama 3.2 90B vs GLM-5.3
Other Meta models
- Muse Spark 1.354.8
- Muse Spark50.6
- Muse Spark 1.250.3
- Muse Spark 1.149.9
- Muse Glimmer41.7
- Codellama 70b Instruct33.7
- Llama 4 Maverick30.9
- Codellama 34b Instruct30.8
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.