DeepSeek-V4-Flash vs Qwen3-235B-A22B-Instruct-2507
DeepSeek vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 72.2)
- •DeepSeek-V4-Flash is cheaper ($0.10 vs $0.15 per 1M input)
- •DeepSeek-V4-Flash is faster
- •DeepSeek-V4-Flash has a larger context window (1M)
| DeepSeek-V4-Flash | Qwen3-235B-A22B-Instruct-2507 | |
|---|---|---|
| Intelligence index | 89.4 | 72.2 |
| Developer | DeepSeek | Alibaba |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 1,048,576 tokens | 131,072 tokens |
| Input price | $0.10 / 1M | $0.15 / 1M |
| Output price | $0.20 / 1M | $0.80 / 1M |
| Speed | 109 tok/s | 63 tok/s |
| Released | April 24, 2026 | July 22, 2025 |
| Parameters | 284B (13B active) | 235000000000 |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek-V4-Flash
Qwen3-235B-A22B-Instruct-2507
GPQA Diamond
89.4
77.5
Humanity’s Last Exam
32.1
10.6