Meta model product
Llama 3.2 90B
2 90B is a large multimodal language model from Meta for visual recognition, image reasoning, and captioning.
Updated Sep 8, 2026. Default version: Llama 3.2 90B Instruct
LLMBoard Score9.3Llama 3.2 90B Instruct
Coverage0%12 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
Llama 3.2 90B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Llama 3.2 90B Benchmark Results
Benchmark scores for Llama 3.2 90B Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkInfographicsQA | Score56.80% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkVQAv2 | Score78.10% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkAI2D | Score92.30% | Rank10 | Participants34 | Percentile72.73% | EvidenceC | Evaluated |
| BenchmarkTextVQA | Score73.50% | Rank12 | Participants16 | Percentile26.67% | EvidenceC | Evaluated |
| BenchmarkChartQA | Score85.50% | Rank13 | Participants26 | Percentile52.00% | EvidenceC | Evaluated |
| BenchmarkMGSM | Score86.90% | Rank14 | Participants31 | Percentile56.67% | EvidenceC | Evaluated |
| BenchmarkDocVQA | Score90.10% | Rank21 | Participants28 | Percentile25.93% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score57.30% | Rank29 | Participants39 | Percentile26.32% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score86.00% | Rank33 | Participants101 | Percentile68.00% | EvidenceC | Evaluated |
| BenchmarkMATH | Score68.00% | Rank44 | Participants71 | Percentile38.57% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score60.30% | Rank45 | Participants64 | Percentile30.16% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score45.20% | Rank63 | Participants69 | Percentile8.82% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,032.50 rating | Rank99 | Participants107 | Percentile7.55% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score999.65 rating | Rank100 | Participants107 | Percentile6.60% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score46.70% | Rank200 | Participants247 | Percentile19.11% | EvidenceC | Evaluated |
Llama 3.2 90B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorychinese | Rank89 | Rating / score951.37 | Votes393 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank89 | Rating / score1,003.14 | Votes393 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank99 | Rating / score1,032.50 | Votes8,682 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank100 | Rating / score1,012.81 | Votes4,630 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank100 | Rating / score999.65 | Votes8,682 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank100 | Rating / score1,039.04 | Votes4,630 | ObservationsN/A | Result date |
Llama 3.2 90B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Llama 3.2 90B Runtime Performance
Provider-specific output speed and catalog latency for Llama 3.2 90B Instruct. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderDeepInfra | Output Speed24.00 tok/s | Catalog Latency0.50 s | Max Input128K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Llama 3.2 90B Specifications
Technical details for the model's default version.
- Version
- Llama 3.2 90B Instruct
- Released
- Sep 25, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 90B
- Context window
- 128K
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- Yes
- License
- Llama 3.2
Llama 3.2 90B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionLlama 3.2 90B Instruct | Released | LLMBoard9.31 | Parameters90B | Context128K | Max output128K | Open weightsYes | LicenseLlama 3.2 |
Models similar to Llama 3.2 90B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ME
Llama 3.1 70B
Meta
ME
Llama 4 Scout
Meta
ME
Llama 3.1 8B
Meta
ME
Llama 3.2 11B
Meta
ME
Llama 3.2 3B
Meta
ME
Llama 3.3 70B
Meta
What is Llama 3.2 90B?
Key information about Llama 3.2 90B and its available data.
2 90B is a large multimodal language model from Meta with a 128,000-token context length. It is designed for deployment on edge and mobile devices and supports image understanding and generative tasks.
Data as of 2026-09-08.
FAQ
Common questions about Llama 3.2 90B.
When was Llama 3.2 90B released?
Llama 3.2 90B's default version was released on Sep 25, 2024.
How much does Llama 3.2 90B cost?
No official standard PAYG price is currently available for Llama 3.2 90B.
Who created Llama 3.2 90B?
Llama 3.2 90B was created by Meta.
What is the context window for Llama 3.2 90B?
The default version has a 128K token context window.
Is Llama 3.2 90B open weight?
Yes. The default version is marked as open weight under Llama 3.2.
How many API providers offer Llama 3.2 90B?
No provider offering is currently linked to the default version.