StepFun: Step 3.7 Flash vs Qwen: Qwen3.6 35B A3B
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| StepFun: Step 3.7 Flash | Qwen: Qwen3.6 35B A3B | |
|---|---|---|
| Vendor | stepfun | qwen |
| Quality Score | 100 | 100 |
| Benchmark Score | 50.8 | 52.9 |
| Input Price | $0.20/M | $0.10/M |
| Output Price | $1.15/M | $0.90/M |
| Context Window | 262,144 | 262,144 |
| Max Output | 230,400 | 235,929 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 49.9 | 52.2 |
| ai_index_agentic | 35.5 | 35.3 |
| ai_index_coding | 65.3 | 69.1 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Qwen3.6 35B A3B costs $0.33 and Step 3.7 Flash costs $0.49, so Qwen3.6 35B A3B is about 1.5 times cheaper for the same work.
Both read up to 262,144 tokens at once, roughly 393 pages of text.
On our blended benchmark score Qwen3.6 35B A3B leads 52.9 to 50.8.
Across the 20 tasks where they differ, Qwen3.6 35B A3B on 20 (SQL Generation, Code Review, Code Completion and others).
Step 3.7 Flash was released in May 2026 and Qwen3.6 35B A3B in April 2026.
Pick Qwen3.6 35B A3B if you need lower cost, benchmark performance or the stronger all-round task scores.
Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.
Who wins by task?
| Task | StepFun: Step 3.7 Flash | Qwen: Qwen3.6 35B A3B |
|---|---|---|
| SQL Generation | 153 | 154 |
| Code Review | 146 | 147 |
| Code Completion | 130 | 130 |
| Code Refactoring | 144 | 144 |
| Bug Fixing | 155 | 156 |
| Unit Test Generation | 139 | 140 |
| Code Documentation | 133 | 133 |
| Regex Writing | 129 | 129 |
| CI/CD Pipelines | 131 | 132 |
| Frontend Component Design | 136 | 137 |
| Data Analysis | 150 | 151 |
| CSV / Spreadsheet Cleanup | 141 | 141 |
| ETL Scripting | 137 | 138 |
| JSON Extraction | 142 | 143 |
| Bulk Data Labeling | 133 | 133 |
| OCR / Document Parsing | 138 | 138 |
| Table Extraction from PDFs | 138 | 138 |
| Long-Document Summarization | 142 | 142 |
| Short-Form Summarization | 128 | 128 |
| Blog Post Writing | 129 | 130 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →