Anthropic: Claude Sonnet 5 vs Google: Gemini 3.5 Flash
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Anthropic: Claude Sonnet 5 | Google: Gemini 3.5 Flash | |
|---|---|---|
| Vendor | anthropic | |
| Quality Score | 100 | 100 |
| Benchmark Score | 91.4 | 84.2 |
| Input Price | $2.00/M | $1.50/M |
| Output Price | $10.00/M | $9.00/M |
| Context Window | 1,000,000 | 1,048,576 |
| Max Output | 128,000 | 65,536 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | ✓ |
| Benchmark Scores | ||
| ai_index | 88.0 | 82.8 |
| ai_index_agentic | 77.0 | 61.8 |
| ai_index_coding | 100.0 | 100.0 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Gemini 3.5 Flash costs $3.75 and Claude Sonnet 5 costs $4.50, so Gemini 3.5 Flash is about 1.2 times cheaper for the same work.
Both take in a similar amount of text: 1,000,000 and 1,048,576 tokens, about 1,500 and 1,573 pages.
Only Gemini 3.5 Flash offers audio input and video input.
On our blended benchmark score Claude Sonnet 5 leads 91.4 to 84.2.
Across the 20 tasks where they differ, Claude Sonnet 5 scores higher on 18 (SQL Generation, Code Review, Code Refactoring and others), Gemini 3.5 Flash on 2 (Code Completion, Bulk Data Labeling).
Claude Sonnet 5 was released in June 2026 and Gemini 3.5 Flash in May 2026.
Pick Claude Sonnet 5 if you need benchmark performance or the stronger all-round task scores; pick Gemini 3.5 Flash if you need lower cost, audio input or video input.
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 | Anthropic: Claude Sonnet 5 | Google: Gemini 3.5 Flash |
|---|---|---|
| SQL Generation | 171 | 168 |
| Code Review | 167 | 164 |
| Code Completion | 119 | 119 |
| Code Refactoring | 164 | 162 |
| Bug Fixing | 180 | 176 |
| Unit Test Generation | 154 | 152 |
| Code Documentation | 141 | 141 |
| Regex Writing | 135 | 133 |
| CI/CD Pipelines | 144 | 143 |
| Frontend Component Design | 146 | 145 |
| Data Analysis | 171 | 167 |
| CSV / Spreadsheet Cleanup | 153 | 153 |
| ETL Scripting | 154 | 152 |
| JSON Extraction | 138 | 138 |
| Bulk Data Labeling | 124 | 124 |
| OCR / Document Parsing | 146 | 146 |
| Table Extraction from PDFs | 146 | 146 |
| Long-Document Summarization | 159 | 157 |
| Short-Form Summarization | 122 | 121 |
| Blog Post Writing | 140 | 138 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →