DeepSeek V3.2 vs Qwen3.6 Plus
Head to head on 20 shared benchmarks, with price, context window, and release dates.
Benchmark scores
46evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen3.6 Plus Alibaba | 61.9% | 23.0% | 26.2% | 88.2% | 27.8% | 75.2% | 83.2% | 73.5% | 78.2% | 69.9% | 58.3% | 75.0% | 83.7% | 75.8% | 40.7% | 74.7% | 43.9% | 59.5 | 25.6% | 97.7% | - | - | - | 95.3 | - | - | - | 40.8% | 96.7 | - | - | - | 36.9% | 77.0% | 88.5 | 94.5 | - | 89.5 | 68.0% | - | 44.9% | 73.8 | - | - | 32.0% | 51.5% | 59.0% |
| DeepSeek V3.2 DeepSeek | 47.9% | 16.0% | 22.1% | 75.1% | 11.2% | 49.0% | 68.0% | 65.9% | 64.6% | 50.0% | 48.2% | 70.4% | 85.0% | 77.2% | 38.7% | 68.2% | 32.6% | 65 | 5.1% | 78.9% | 74.7% | 74.2% | 59.0% | - | 0.0% | 1511elo | 66.8 | - | - | 31.3% | 59.3% | 57.5% | - | - | - | - | 83.7% | - | - | 8.0% | - | - | 59.0% | 70.0% | - | - | 51.7% |
2 / 2 models
| Attribute | DeepSeek V3.2 DeepSeek | Qwen3.6 Plus Alibaba |
|---|---|---|
| Description | DeepSeek V3.2 is an AI model from DeepSeek, released with open weights. | Qwen3.6Plus is an AI model from Alibaba. |
| Family | Deepseek | Qwen3.6 |
| Params | - | - |
| Open weights | open | closed |
| License | mit | proprietary |
| Released | 1 Dec 2025 | 2 Apr 2026 |
| Context | 163,840 | 1,000,000 |
| Input $/1M | $0.28 | $0.50 |
| Output $/1M | $0.42 | $3.00 |
| Cache read $/1M | $0.130 | - |
| Cache write $/1M | - | $0.406 |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text | text, image, video |
| Providers | - | - |
| Publisher | DeepSeek | Alibaba |
| Reported scores | Aider Polyglot Benchmark74.2% (Aider) MathArena57.47% GPQA Diamond75.1% (AA) Humanity's Last Exam (HLE)11.2% (AA) | GPQA Diamond88.2% (AA) Humanity's Last Exam (HLE)27.8% (AA) IFBench75.2% (AA) SciCode40.7% (AA) τ²-bench (Tau²-bench)97.7% (AA) |
FAQ
- Is DeepSeek V3.2 or Qwen3.6 Plus better?
- Across the 20 benchmarks both models report on Sophon, Qwen3.6 Plus leads on 17 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do DeepSeek V3.2 and Qwen3.6 Plus compare on GPQA Diamond?
- DeepSeek V3.2 scores 75.1% and Qwen3.6 Plus scores 88.2% on GPQA Diamond.
- Which is cheaper, DeepSeek V3.2 or Qwen3.6 Plus?
- DeepSeek V3.2 is cheaper at $0.42 per million output tokens against $3.00 for Qwen3.6 Plus - about 7.1x.
- When were DeepSeek V3.2 and Qwen3.6 Plus released?
- DeepSeek V3.2 was released 1 Dec 2025 by DeepSeek. Qwen3.6 Plus was released 2 Apr 2026 by Alibaba.
Comparing something else? Build your own side-by-side.