DeepSeek-V4-Flash vs Qwen3-235B-A22B-Thinking-2507
DeepSeek vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 79.6)
- •DeepSeek-V4-Flash is cheaper ($0.10 vs $0.30 per 1M input)
- •DeepSeek-V4-Flash has a larger context window (1M)
| DeepSeek-V4-Flash | Qwen3-235B-A22B-Thinking-2507 | |
|---|---|---|
| Intelligence index | 89.4 | 79.6 |
| Developer | DeepSeek | Alibaba |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 1,048,576 tokens | 256,000 tokens |
| Input price | $0.10 / 1M | $0.30 / 1M |
| Output price | $0.20 / 1M | $3.00 / 1M |
| Speed | 109 tok/s | — |
| Released | April 24, 2026 | July 25, 2025 |
| Parameters | 284B (13B active) | 235000000000 |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
DeepSeek-V4-Flash
Qwen3-235B-A22B-Thinking-2507
GPQA Diamond
89.4
81.1
Humanity’s Last Exam
32.1
18.2