Qwen3 235B-A22B Instruct 2507 vs Qwen3.5 9B
| Spec | Qwen3 235B-A22B Instruct 2507 | Qwen3.5 9B |
|---|---|---|
| Respan Index | 20.2 (#126) | 20.6 (#124) |
| Blended price per 1M | $0.205 | $0.1 |
| Context window | 262K | 262K |
| Input / output per 1M | $0.09 / $0.55 | $0.09 / $0.13 |
| Max output | - | - |
| Input | text | text, vision, video |
| Released | 2025-07-21 | 2026-03-02 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Qwen3 235B-A22B Instruct 2507 | Qwen3.5 9B |
|---|---|---|
| Coding | 4.7 Qwen3 235B-A22B Instruct 2507 | 2.4 Qwen3.5 9B |
| Agents | 17.9* Qwen3 235B-A22B Instruct 2507 | 23.8 Qwen3.5 9B |
| Reasoning | 22.6* Qwen3 235B-A22B Instruct 2507 | 23.6 Qwen3.5 9B |
| Knowledge & language | 16.2 Qwen3 235B-A22B Instruct 2507 | 15.8 Qwen3.5 9B |
| Human preference | 48.6 Qwen3 235B-A22B Instruct 2507 | 43.5* Qwen3.5 9B |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
Qwen3 235B-A22B Instruct 2507 leads on 3 of the 4 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Qwen3 235B-A22B Instruct 2507 | Qwen3.5 9B |
|---|---|---|
| IFEval | 88.7% | 91.5% |
| MMLU-Pro | 83% | 82.5% |
| MMLU-Redux | 93.1% | 91.1% |
| SuperGPQA | 62.6% | 58.2% |
FAQ
Is Qwen3 235B-A22B Instruct 2507 better than Qwen3.5 9B?
Qwen3.5 9B scores 20.6 on the Respan Index (#124), ahead of Qwen3 235B-A22B Instruct 2507 at 20.2 (#126). Qwen3 235B-A22B Instruct 2507 leads on 3 of the 4 benchmarks both report.
Which is cheaper, Qwen3 235B-A22B Instruct 2507 or Qwen3.5 9B?
Qwen3 235B-A22B Instruct 2507 lists at $0.09 input and $0.55 output per 1M tokens; Qwen3.5 9B at $0.09 and $0.13. Qwen3.5 9B is 2.0x cheaper per token at list price.
Which has the larger context window?
Both accept 262K tokens of context.