Llama 4 Maverick vs Qwen3.5 397B A17B
Meta vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •Qwen3.5 397B A17B has the higher intelligence index (89.3 vs 63.9)
- •Llama 4 Maverick is cheaper ($0.15 vs $0.39 per 1M input)
- •Llama 4 Maverick is faster
- •Llama 4 Maverick has a larger context window (1M)
| Llama 4 Maverick | Qwen3.5 397B A17B | |
|---|---|---|
| Intelligence index | 63.9 | 89.3 |
| Developer | Meta | Alibaba |
| Type | Multimodal | Multimodal |
| Access | Open weights | Open weights |
| Context window | 1,048,576 tokens | 262,144 tokens |
| Input price | $0.15 / 1M | $0.39 / 1M |
| Output price | $0.60 / 1M | $2.34 / 1M |
| Speed | 639 tok/s | 53 tok/s |
| Released | April 5, 2025 | February 16, 2026 |
| Parameters | 400B total / 17B active (MoE) | — |
| Input modalities | Text, Image | Text, Image, Video |
| Output modalities | Text | Text |
Shared benchmarks
Llama 4 Maverick
Qwen3.5 397B A17B
GPQA Diamond
69.8
89.3
Humanity’s Last Exam
4.8
27.3