Google: Gemini 3.1 Pro Preview vs Anthropic: Claude Sonnet 4.6
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Google: Gemini 3.1 Pro Preview | Anthropic: Claude Sonnet 4.6 | |
|---|---|---|
| Vendor | anthropic | |
| Quality Score | 100 | 100 |
| Benchmark Score | 74.7 | 80.1 |
| Input Price | $2.00/M | $3.00/M |
| Output Price | $12.00/M | $15.00/M |
| Context Window | 1,048,576 | 1,000,000 |
| Max Output | 65,536 | 128,000 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | ✓ | - |
| Benchmark Scores | ||
| ai_index | 76.7 | 77.9 |
| ai_index_agentic | 35.3 | 67.3 |
| ai_index_coding | 100.0 | 100.0 |
| aider_polyglot | - | 61.3 |
| eqbench | 64.7 | 68.4 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Gemini 3.1 Pro Preview costs $5.00 and Claude Sonnet 4.6 costs $6.75, so Gemini 3.1 Pro Preview is about 1.4 times cheaper for the same work.
Both take in a similar amount of text: 1,048,576 and 1,000,000 tokens, about 1,573 and 1,500 pages.
Only Gemini 3.1 Pro Preview offers audio input and video input.
On our blended benchmark score Claude Sonnet 4.6 leads 80.1 to 74.7.
Across the 20 tasks where they differ, Gemini 3.1 Pro Preview scores higher on 1 (Code Completion), Claude Sonnet 4.6 on 19 (SQL Generation, Code Review, Code Refactoring and others).
Pick Gemini 3.1 Pro Preview if you need lower cost, audio input or video input; pick Claude Sonnet 4.6 if you need 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 | Google: Gemini 3.1 Pro Preview | Anthropic: Claude Sonnet 4.6 |
|---|---|---|
| SQL Generation | 168 | 183 |
| Code Review | 168 | 183 |
| Code Completion | 120 | 120 |
| Code Refactoring | 168 | 179 |
| Bug Fixing | 177 | 196 |
| Unit Test Generation | 154 | 166 |
| Code Documentation | 144 | 148 |
| Regex Writing | 133 | 139 |
| CI/CD Pipelines | 145 | 155 |
| Frontend Component Design | 145 | 154 |
| Data Analysis | 164 | 183 |
| CSV / Spreadsheet Cleanup | 155 | 163 |
| ETL Scripting | 156 | 167 |
| JSON Extraction | 137 | 142 |
| Bulk Data Labeling | 123 | 124 |
| OCR / Document Parsing | 147 | 152 |
| Table Extraction from PDFs | 147 | 152 |
| Long-Document Summarization | 163 | 172 |
| Short-Form Summarization | 121 | 124 |
| Blog Post Writing | 140 | 147 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →