Llama 3.2 90B Vision Instruct
MetaOpenLlama 3.2
Llama 3.2 90B Vision Instruct is a vision-language model from Meta. It ranks 149 of 167 on LMArena’s overall vision board with 1000±9 from 8,682 votes. License: Llama 3.2.
Key figures
- Developer
- Meta
- License
- Llama 3.2
- First seen (our snapshots)
- 2026-10-26
No data: OCR, Diagrams, Homework, Captioning, Entity recognition, Creative writing, Humor.
Who it suits
- Overall #149 of 167: lower half; consider it mainly for cost or deployment reasons.
- Open weights (Llama 3.2): you can self-host it.
Neighbours on the overall board
| # | Model | Score | Votes | License | Δ vs this model |
|---|---|---|---|---|---|
| 146 |  Pixtral 12B (2409) Mistral | 1009 | 7,511 | Apache 2.0 | +9 |
| 147 |  Gemini 1.5 Flash (001) Google | 1008 | 13,260 | Proprietary | +8 |
| 148 | OInternVL2 26B OpenGVLab | 1005 | 5,148 | MIT | +5 |
| 149 | Llama 3.2 90B Vision Instruct Meta | 1000 | 8,682 | Llama 3.2 | |
| 150 |  Hunyuan Standard Vision (2024-12-31) Tencent | 999 | 809 | Proprietary | -1 |
| 151 |  Aya Vision 32B Cohere | 996 | 847 | CC-BY-NC-4.0 | -4 |
| 152 | AAmazon Nova Lite 1.0 Amazon | 990 | 1,854 | Proprietary | -10 |
Alternatives · More from Meta
| # | Model | Score | Votes | License |
|---|---|---|---|---|
| 12 | Muse Spark 1.3 (Max) Meta | 1308 | 5,392 | Proprietary |
| 15 | Muse Spark Meta | 1306 | 5,865 | Proprietary |
| 17 | Muse Spark 1.2 (xHigh) Meta | 1304 | 1,948 | Proprietary |
| 19 | Muse Spark 1.3 (xHigh) Meta | 1302 | 4,897 | Proprietary |
| 26 | Muse Spark 1.1 Meta | 1293 | 12,804 | Proprietary |
Alternatives · Top open-weight models
| # | Model | Score | Votes | License |
|---|---|---|---|---|
| 24 |  GLM-5.3-Flash Z.ai | 1294 | 16,254 | MIT |
| 34 |  Kimi K2.6 Moonshot AI | 1282 | 16,368 | Modified MIT |
| 38 |  DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek | 1278 | 4,100 | MIT |
| 39 | Gemma 4 31B Google | 1276 | 40,219 | Apache 2.0 |
| 44 |  Qwen3.8-27B Alibaba | 1269 | 7,614 | Apache 2.0 |
How to read these scores
- If two scores differ by less than their ± intervals, the models are statistically close.
- Each category board is computed independently; do not compare scores across categories.
- Models with few votes move more; ranks of new entries may change.
FAQ
Where does Llama 3.2 90B Vision Instruct rank among vision models?
Overall rank 149 (1000); English rank 150 (1013); Chinese rank 120 (952) (LMArena, data as of Oct 26, 2026).
How good is Llama 3.2 90B Vision Instruct at OCR?
Llama 3.2 90B Vision Instruct is not on LMArena’s OCR board yet, so there is no score to cite.
Is Llama 3.2 90B Vision Instruct better with Chinese or English prompts?
Chinese board: #120 of 128 (952); English board: #150 of 167 (1013). The boards are computed separately, so compare ranks rather than scores.
Is Llama 3.2 90B Vision Instruct open-weight?
LMArena lists its license as Llama 3.2, not proprietary; check the license text for commercial use.
How far is Llama 3.2 90B Vision Instruct from #1?
#1 overall is Claude Fable 5 (High) (1325); Llama 3.2 90B Vision Instruct has 1000, 325 points behind.
Sources
LMArena data published Oct 19, 2026.
Synced here Oct 26, 2026.
Price, context length and release date have no reliable public data here and are not shown; all figures come from snapshots, blanks are –.