Compare / Qwen3 30B-A3B Thinking 2507 vs Qwen3-Coder 30B-A3B
Qwen3 30B-A3B Thinking 2507 vs Qwen3-Coder 30B-A3B
Updated November 2026
Verdict
Qwen3 30B-A3B Thinking 2507 scores higher on the Small LM Index: 65.4 vs 34.9. On the 10 benchmarks both labs report, Qwen3 30B-A3B Thinking 2507 wins 8 and Qwen3-Coder 30B-A3B wins 2. Both need about 20.4 GB of memory at 4-bit quantization. Only Qwen3-Coder 30B-A3B has a hosted API on OpenRouter ($0.12 per million tokens); the other has to be self-hosted.
Pick Qwen3 30B-A3B Thinking 2507 if…
- you want the strongest model overall
- you need math and reasoning
- you need precise instruction following
Pick Qwen3-Coder 30B-A3B if…
- you build agents that call tools
- you want a hosted API rather than running it yourself
- you want the more widely used model (more quantized builds and community support)
Specifications
| Qwen3 30B-A3B Thinking 2507 | Qwen3-Coder 30B-A3B | |
|---|---|---|
| Small LM Index | 65.4 (likely 63–67) | 34.9 (likely 32–38) |
| Lab | Alibaba (Qwen) · China | Alibaba (Qwen) · China |
| Released | 2025-07-30 | 2025-07-31 |
| Parameters | 30.5B (3.3B active, MoE) | 30.5B (3.3B active, MoE) |
| Memory at 4-bit | ~20.4 GB | ~20.4 GB |
| Context window | 262K tokens | 262K tokens |
| Input | text | text |
| Reasoning | Always thinks | No thinking |
| License | Apache-2.0 | Apache-2.0 |
| API price / 1M tokens | Self-host only | $0.12 ($0.070 in, $0.28 out) |
| Hugging Face downloads (30 days) | 68K | 1.3M |
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 30B-A3B Thinking 2507 | Qwen3-Coder 30B-A3B |
|---|---|---|
| MMLU-Pro Knowledge | 80.5✓ | 70.6✓ |
| GPQA Diamond Knowledge | 70.7✓ | 51.6✓ |
| Humanity's Last Exam Reasoning | 10.3✓ | 3.8✓ |
| AIME Math | 90.7✓ | 29.7✓ |
| LiveCodeBench Coding | 70.7✓ | 40.3✓ |
| SWE-bench Verified Coding | 22.0* | 51.6 |
| τ²-Bench Agentic | 28.1✓ | 34.5✓ |
| IFBench Instruction following | 50.7✓ | 32.7✓ |
| MATH-500 Math | 97.6✓ | 89.3✓ |
| AA-LCR Long context | 61.3✓ | 32.7✓ |
| SciCode Coding | 33.0✓ | — |
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 30B-A3B Thinking 2507 or Qwen3-Coder 30B-A3B?
Qwen3 30B-A3B Thinking 2507 scores higher on the Small LM Index: 65.4 vs 34.9. On the 10 benchmarks both labs report, Qwen3 30B-A3B Thinking 2507 wins 8 and Qwen3-Coder 30B-A3B wins 2.
Which is cheaper to run?
Only Qwen3-Coder 30B-A3B has a hosted API on OpenRouter ($0.12 per million tokens); the other has to be self-hosted. Both need about 20.4 GB of memory at 4-bit quantization.
Which has the longer context window?
Both have a 262K-token context window.
Can I use Qwen3 30B-A3B Thinking 2507 and Qwen3-Coder 30B-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
- Muse Glimmer 30B vs Qwen3 30B-A3B Thinking 2507
- Gemma 4 31B vs Qwen3 30B-A3B Thinking 2507
- GLM-4.7-Flash vs Qwen3 30B-A3B Thinking 2507
- Granite 4.2 30B vs Qwen3 30B-A3B Thinking 2507
- Kanana-2 30B-A3B Thinking vs Qwen3 30B-A3B Thinking 2507
- North Mini Code vs Qwen3 30B-A3B Thinking 2507
- Muse Glimmer 30B vs Qwen3-Coder 30B-A3B
- Gemma 4 31B vs Qwen3-Coder 30B-A3B
- GLM-4.7-Flash vs Qwen3-Coder 30B-A3B
- Granite 4.2 30B vs Qwen3-Coder 30B-A3B