Compare / Qwen3.6 35B-A3B vs Qwen3.5 35B-A3B
Qwen3.6 35B-A3B vs Qwen3.5 35B-A3B
Updated November 2026
Verdict
Qwen3.6 35B-A3B scores higher on the Small LM Index: 72.2 vs 69.9, although their likely ranges overlap, so the lead is not certain. On the 8 benchmarks both labs report, Qwen3.6 35B-A3B wins 6 and Qwen3.5 35B-A3B wins 2. Both need about 22.6 GB of memory at 4-bit quantization. Qwen3.6 35B-A3B is cheaper through an API: $0.031 per million tokens against $0.24.
Pick Qwen3.6 35B-A3B if…
- you want the strongest model overall
- you mostly write code
- you need math and reasoning
- you build agents that call tools
- API cost matters most
Pick Qwen3.5 35B-A3B if…
No clear advantage in the data we have.
Specifications
| Qwen3.6 35B-A3B | Qwen3.5 35B-A3B | |
|---|---|---|
| Small LM Index | 72.2 (likely 71–74) | 69.9 (likely 69–71) |
| Lab | Alibaba (Qwen) · China | Alibaba (Qwen) · China |
| Released | 2026-04-16 | 2026-02-24 |
| Parameters | 35B (3B active, MoE) | 35B (3B active, MoE) |
| Memory at 4-bit | ~22.6 GB | ~22.6 GB |
| Context window | 262K tokens | 262K tokens |
| Input | text, image, video | text, image, video |
| Reasoning | Hybrid (thinking on/off) | Hybrid (thinking on/off) |
| License | Apache-2.0 | Apache-2.0 |
| API price / 1M tokens | $0.031 ($0.010 in, $0.092 out) | $0.24 ($0.065 in, $0.75 out) |
| Hugging Face downloads (30 days) | 4.5M | 1.7M |
Benchmarks
Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.
| Benchmark | Qwen3.6 35B-A3B | Qwen3.5 35B-A3B |
|---|---|---|
| MMLU-Pro Knowledge | 85.2 | 85.3 |
| GPQA Diamond Knowledge | 86.0 | 84.2 |
| Humanity's Last Exam Reasoning | 21.4 | 22.4 |
| AIME Math | 92.7 | 91.0 |
| LiveCodeBench Coding | 80.4 | 74.6 |
| SWE-bench Verified Coding | 73.4 | 70.0 |
| Terminal-Bench Agentic | 51.5 | 40.5 |
| MMMU-Pro Vision | 75.3 | 75.1 |
Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.
Questions
Which is better, Qwen3.6 35B-A3B or Qwen3.5 35B-A3B?
Qwen3.6 35B-A3B scores higher on the Small LM Index: 72.2 vs 69.9, although their likely ranges overlap, so the lead is not certain. On the 8 benchmarks both labs report, Qwen3.6 35B-A3B wins 6 and Qwen3.5 35B-A3B wins 2.
Which is cheaper to run?
Qwen3.6 35B-A3B is cheaper through an API: $0.031 per million tokens against $0.24. Both need about 22.6 GB of memory at 4-bit quantization.
Which has the longer context window?
Both have a 262K-token context window.
Can I use Qwen3.6 35B-A3B and Qwen3.5 35B-A3B commercially?
Both are released under the Apache-2.0 license. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.
Related comparisons
- MiniCPM-V 4.7 35B-A3B vs Qwen3.6 35B-A3B
- Edge0 35B-A3B (preview) vs Qwen3.6 35B-A3B
- Qwen3.6 35B-A3B vs Seed-OSS 36B Instruct
- Hermes 4.3 36B vs Qwen3.6 35B-A3B
- MiniCPM-V 4.7 35B-A3B vs Qwen3.5 35B-A3B
- Edge0 35B-A3B (preview) vs Qwen3.5 35B-A3B
- Qwen3.5 35B-A3B vs Seed-OSS 36B Instruct
- Hermes 4.3 36B vs Qwen3.5 35B-A3B