Compare / Qwen3.8 27B vs Qwen3.5 27B
Qwen3.8 27B vs Qwen3.5 27B
Updated November 2026
Verdict
Qwen3.8 27B scores higher on the Small LM Index: 77.0 vs 70.6. On the 4 benchmarks both labs report, Qwen3.8 27B wins 4 and Qwen3.5 27B wins 0. Both need about 17.9 GB of memory at 4-bit quantization. Qwen3.8 27B is cheaper through an API: $0.13 per million tokens against $0.69.
Pick Qwen3.8 27B if…
- you want the strongest model overall
- you mostly write code
- you build agents that call tools
- API cost matters most
- you want the more widely used model (more quantized builds and community support)
Pick Qwen3.5 27B if…
No clear advantage in the data we have.
Specifications
| Qwen3.8 27B | Qwen3.5 27B | |
|---|---|---|
| Small LM Index | 77.0 (likely 76–79) | 70.6 (likely 69–72) |
| Lab | Alibaba (Qwen) · China | Alibaba (Qwen) · China |
| Released | 2026-08-14 | 2026-02-24 |
| Parameters | 27B (dense) | 27B (dense) |
| Memory at 4-bit | ~17.9 GB | ~17.9 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 | $0.13 ($0.009 in, $0.49 out) | $0.69 ($0.25 in, $2.00 out) |
| Hugging Face downloads (30 days) | 8M | 1.8M |
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 | Qwen3.8 27B | Qwen3.5 27B |
|---|---|---|
| MMLU-Pro Knowledge | ≈ 86 | 86.1 |
| GPQA Diamond Knowledge | 89.2 | 85.5 |
| Humanity's Last Exam Reasoning | 30.8 | 24.3 |
| AIME Math | ≈ 96 | 92.6 |
| LiveCodeBench Coding | 90.3 | 80.7 |
| SWE-bench Verified Coding | ≈ 77 | 75.0 |
| Terminal-Bench Agentic | 73.0 | 41.6 |
| IFBench Instruction following | 79.5 | — |
| MMMU-Pro Vision | — | 75.0 |
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, Qwen3.8 27B or Qwen3.5 27B?
Qwen3.8 27B scores higher on the Small LM Index: 77.0 vs 70.6. On the 4 benchmarks both labs report, Qwen3.8 27B wins 4 and Qwen3.5 27B wins 0.
Which is cheaper to run?
Qwen3.8 27B is cheaper through an API: $0.13 per million tokens against $0.69. Both need about 17.9 GB of memory at 4-bit quantization.
Which has the longer context window?
Both have a 262K-token context window.
Can I use Qwen3.8 27B and Qwen3.5 27B 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.