token.app › Compare › Qwen3.6 35B A3B vs DeepSeek V4 Flash 0731
Qwen3.6 35B A3B vs DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads on 3 of 3 shared benchmarks. Qwen3.6 35B A3B is 2.1× cheaper per token on a blended 3:1 basis. DeepSeek V4 Flash 0731 accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| Qwen3.6 35B A3B | DeepSeek V4 Flash 0731 | |
|---|---|---|
| Provider | Alibaba | DeepSeek |
| Input $/1M | $0.100 | $0.440 |
| Output $/1M | $0.950 | $1.32 |
| Blended $/1M | $0.313 | $0.660 |
| Context window | 262K | 1.0M |
| Max output | 236K | 131K |
| Released | Apr 2026 | Jul 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 84.8% | 91.0% |
| FrontierMath T1–3 | 20.4% | 57.5% |
| OTIS Mock AIME | 86.7% | 94.4% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Qwen3.6 35B A3B if…
- Costs less per token — $0.313 vs $0.660 blended
Choose DeepSeek V4 Flash 0731 if…
- Higher GPQA Diamond (91.0% vs 84.8%)
- Higher FrontierMath T1–3 (57.5% vs 20.4%)
- Higher OTIS Mock AIME (94.4% vs 86.7%)
- Larger context window (1.0M)
- Newer model (released Jul 2026)
FAQ
Which is better, Qwen3.6 35B A3B or DeepSeek V4 Flash 0731?
Across the 3 benchmarks both models have independently-run scores for, Qwen3.6 35B A3B leads on 0 and DeepSeek V4 Flash 0731 leads on 3. Benchmarks are one input — price and context window are on this page too.
Is Qwen3.6 35B A3B cheaper than DeepSeek V4 Flash 0731?
Qwen3.6 35B A3B is cheaper: $0.313 versus $0.660 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $0.440. Output alone: $0.950 vs $1.32.
What context windows do Qwen3.6 35B A3B and DeepSeek V4 Flash 0731 have?
Qwen3.6 35B A3B: 262,144 tokens. DeepSeek V4 Flash 0731: 1,048,576 tokens.
Who makes Qwen3.6 35B A3B and DeepSeek V4 Flash 0731?
Qwen3.6 35B A3B is made by Alibaba. DeepSeek V4 Flash 0731 is made by DeepSeek.
Related comparisons