Google: Gemma 4 31B vs Qwen: Qwen3.5-122B-A10B
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Google: Gemma 4 31B | Qwen: Qwen3.5-122B-A10B | |
|---|---|---|
| Vendor | qwen | |
| Quality Score | 100 | 100 |
| Benchmark Score | 53.7 | 54.9 |
| Input Price | $0.20/M | $0.26/M |
| Output Price | $0.40/M | $2.08/M |
| Context Window | 262,144 | 262,144 |
| Max Output | 16,384 | 65,536 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 48.4 | 53.3 |
| ai_index_agentic | 23.8 | 34.2 |
| ai_index_coding | 71.7 | 75.4 |
| eqbench | 57.5 | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Gemma 4 31B costs $0.30 and Qwen3.5-122B-A10B costs $0.78, so Gemma 4 31B is about 2.6 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 Qwen3.5-122B-A10B leads 54.9 to 53.7.
Across the 20 tasks where they differ, Gemma 4 31B scores higher on 18 (SQL Generation, Code Review, Code Completion and others), Qwen3.5-122B-A10B on 2 (Data Analysis, JSON Extraction).
Gemma 4 31B was released in April 2026 and Qwen3.5-122B-A10B in February 2026.
Pick Gemma 4 31B if you need lower cost or the stronger all-round task scores; pick Qwen3.5-122B-A10B if you need benchmark performance.
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 | Google: Gemma 4 31B | Qwen: Qwen3.5-122B-A10B |
|---|---|---|
| SQL Generation | 156 | 155 |
| Code Review | 152 | 148 |
| Code Completion | 131 | 129 |
| Code Refactoring | 151 | 145 |
| Bug Fixing | 160 | 156 |
| Unit Test Generation | 143 | 140 |
| Code Documentation | 137 | 133 |
| Regex Writing | 131 | 129 |
| CI/CD Pipelines | 135 | 132 |
| Frontend Component Design | 138 | 137 |
| Data Analysis | 152 | 152 |
| CSV / Spreadsheet Cleanup | 145 | 142 |
| ETL Scripting | 143 | 139 |
| JSON Extraction | 143 | 143 |
| Bulk Data Labeling | 133 | 133 |
| OCR / Document Parsing | 140 | 139 |
| Table Extraction from PDFs | 140 | 139 |
| Long-Document Summarization | 149 | 143 |
| Short-Form Summarization | 129 | 128 |
| Blog Post Writing | 133 | 130 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →