Llama-3.2-90B-Vision-Instruct
| Released | 2024-09-25 |
|---|---|
| Price per 1M | $0.000 in · $0.000 out |
| Overall score | 36.9 · rank 208 |
| Context window | 128,000 tokens |
| Provider | Meta |
| Weights | Open weights (Llama 3.2 Community License) |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 36.9 | 208 | 7 |
| Overall: Coding | 40.7 | 185 | 3 |
| Overall: Reasoning | 33.5 | 225 | 4 |
| Overall: Agentic work | 42.0 | 182 | 3 |
| Overall: Frontend | 25.3 | 222 | 2 |
| Agents | 44.0 | 141 | 1 |
| Reasoning | 34.2 | 223 | 2 |
| Math | 32.6 | 190 | 2 |
| Multimodal | 25.3 | 120 | 2 |
Evidence
Agents 44.0 ±7.1
Reasoning 34.2 ±3.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 41.0% | Epoch AI | 2025-01-27 |
| EnigmaEval | 0.4% | Epoch AI | 2026-11-11 |
Math 32.6 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MATH Level 5 | 39.4% | Epoch AI | 2025-01-27 |
| OTIS Mock AIME 2024-2025 | 2.6% | Epoch AI | 2025-02-25 |
Multimodal 25.3 ±4.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,032 | LMArena | 2026-11-09 |
| GeoBench | 52.0% | Epoch AI | 2026-11-11 |
Names matched to this model
llama-3-2-90b-vision, llama-3-2-90b-vision-instruct