Llama 3.2 90B Instruct vs Qwen3.7 Max
Meta vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •Qwen3.7 Max has the higher intelligence index (92.3 vs 54)
- •Llama 3.2 90B Instruct is cheaper ($0.35 vs $2.50 per 1M input)
- •Qwen3.7 Max is faster
- •Qwen3.7 Max has a larger context window (1M)
| Llama 3.2 90B Instruct | Qwen3.7 Max | |
|---|---|---|
| Intelligence index | 54 | 92.3 |
| Developer | Meta | Alibaba |
| Type | Multimodal | LLM |
| Access | Open weights | API only |
| Context window | 128,000 tokens | 1,000,000 tokens |
| Input price | $0.35 / 1M | $2.50 / 1M |
| Output price | $0.40 / 1M | $7.50 / 1M |
| Speed | 100 tok/s | 203 tok/s |
| Released | September 25, 2024 | May 21, 2026 |
| Parameters | 90000000000 | — |
| Input modalities | — | Text |
| Output modalities | — | Text |
Shared benchmarks
Llama 3.2 90B Instruct
Qwen3.7 Max
GPQA Diamond
46.7
92.3
Humanity’s Last Exam
4.9
38.1