Compare / Qwen3.5 35B-A3B vs Edge0 35B-A3B (preview)
Qwen3.5 35B-A3B vs Edge0 35B-A3B (preview)
Updated November 2026
Verdict
Qwen3.5 35B-A3B scores higher on the Small LM Index: 69.9 vs 62.8. On the 3 benchmarks both labs report, Qwen3.5 35B-A3B wins 3 and Edge0 35B-A3B (preview) wins 0. Both need about 22.6 GB of memory at 4-bit quantization. Only Qwen3.5 35B-A3B has a hosted API on OpenRouter ($0.24 per million tokens); the other has to be self-hosted.
Pick Qwen3.5 35B-A3B if…
- you want the strongest model overall
- you need math and reasoning
- you want a hosted API rather than running it yourself
- you want the more widely used model (more quantized builds and community support)
Pick Edge0 35B-A3B (preview) if…
No clear advantage in the data we have.
Specifications
| Qwen3.5 35B-A3B | Edge0 35B-A3B (preview) | |
|---|---|---|
| Small LM Index | 69.9 (likely 69–71) | 62.8 (likely 59–67) |
| Lab | Alibaba (Qwen) · China | Edge0 · Other |
| Released | 2026-02-24 | 2026-09-08 |
| Parameters | 35B (3B active, MoE) | 34.7B (3B active, MoE) |
| Memory at 4-bit | ~22.6 GB | ~22.4 GB |
| Context window | 262K tokens | 262K tokens |
| Input | text, image, video | text, image |
| Reasoning | Hybrid (thinking on/off) | Hybrid (thinking on/off) |
| License | Apache-2.0 | Apache-2.0 |
| API price / 1M tokens | $0.24 ($0.065 in, $0.75 out) | Self-host only |
| Hugging Face downloads (30 days) | 1.7M | 4.2K |
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 | Qwen3.5 35B-A3B | Edge0 35B-A3B (preview) |
|---|---|---|
| MMLU-Pro Knowledge | 85.3 | 81.0 |
| GPQA Diamond Knowledge | 84.2 | 79.8 |
| Humanity's Last Exam Reasoning | 22.4 | ≈ 12 |
| AIME Math | 91.0 | 86.6 |
| LiveCodeBench Coding | 74.6 | ≈ 72 |
| SWE-bench Verified Coding | 70.0 | ≈ 50 |
| Terminal-Bench Agentic | 40.5 | — |
| IFBench Instruction following | — | 57.9 |
| MMMU-Pro Vision | 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, Qwen3.5 35B-A3B or Edge0 35B-A3B (preview)?
Qwen3.5 35B-A3B scores higher on the Small LM Index: 69.9 vs 62.8. On the 3 benchmarks both labs report, Qwen3.5 35B-A3B wins 3 and Edge0 35B-A3B (preview) wins 0.
Which is cheaper to run?
Only Qwen3.5 35B-A3B has a hosted API on OpenRouter ($0.24 per million tokens); the other has to be self-hosted. 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 Qwen3.5 35B-A3B and Edge0 35B-A3B (preview) 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.