Meta • text#468 of 579 in intelligence
Context Window
—
Input Price/1M
—
#1 of 714
Output Price/1M
—
Parameters
—
Llama 3.2 Instruct 90B (Vision) results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| SciCode | 24.0 | 100.0 | — |
| LiveCodeBench | 21.0 | 100.0 | Artificial Analysis official API |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU-Pro | 67.0 | 100.0 | — |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MATH-500 | 62.9 | 100.0 | Artificial Analysis official API |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Intelligence Index | 6.0 | 100.0 | Artificial Analysis official API |
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU Pro | 67.1 | 100.0 | Artificial Analysis official API |
| GPQA Diamond | 43.0 | 100.0 | Artificial Analysis official API |
| HLE | 5.0 | 100.0 | — |
Llama 3.2 Instruct 90B (Vision) is an AI model developed by Meta, classified as a text model. It focuses on text processing and natural language generation. As a proprietary model, it is available via Meta's cloud API.
Llama 3.2 Instruct 90B (Vision) does not have public per-token pricing available at this time. Some models offer access via enterprise plans or research programs. Check Meta's official website for up-to-date availability and pricing.
Llama 3.2 Instruct 90B (Vision) was evaluated on 8 different benchmarks, covering categories like Coding, Knowledge, Math, overall, Reasoning. Results show moderate performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Llama 3.2 Instruct 90B (Vision) specializes in text, offering advanced capabilities for creating and processing text content.
In the 2026 AI model ecosystem, Llama 3.2 Instruct 90B (Vision) competes directly with similarly capable models. As an open source model, it competes with Qwen (Alibaba), Mistral, and DeepSeek, as well as proprietary models like GPT, Claude, and Gemini. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Llama 3.2 Instruct 90B (Vision) is an AI model developed by Meta. It is a text model.
Llama 3.2 Instruct 90B (Vision) does not have public per-token pricing available at this time. Check Meta's official website for up-to-date information.
In available benchmarks, Llama 3.2 Instruct 90B (Vision) scored: SciCode: 24/100, LiveCodeBench: 21/100, MMLU-Pro: 67/100. See the full table above for a detailed comparison.
No, Llama 3.2 Instruct 90B (Vision) is a proprietary model from Meta. It is available via cloud API. For open source alternatives, check our open source model ranking.
Llama 3.2 Instruct 90B (Vision) excels at general-purpose language tasks.
Last updated: September 01, 2026 • View methodology →