Google: Gemini 3.7 Flash vs Anthropic: Claude Sonnet 5
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-09-28.
| Google: Gemini 3.7 Flash | Anthropic: Claude Sonnet 5 | |
|---|---|---|
| Vendor | anthropic | |
| Quality Score | 100 | 100 |
| Benchmark Score | 65.5 | 63.9 |
| Input Price | $0.75/M | $2.00/M |
| Output Price | $3.75/M | $10.00/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 | 64.4 | 63.0 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Gemini 3.7 Flash costs $1.69 and Claude Sonnet 5 costs $4.50, so Gemini 3.7 Flash is about 2.7 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 3.7 Flash offers audio input and video input.
On our blended benchmark score Gemini 3.7 Flash leads 65.5 to 63.9.
Across the 18 tasks where they differ, Gemini 3.7 Flash scores higher on 18 (SQL Generation, Code Review, Code Completion and others).
Gemini 3.7 Flash was released in August 2026 and Claude Sonnet 5 in June 2026.
Pick Gemini 3.7 Flash if you need lower cost, audio input, video input, 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 3.7 Flash | Anthropic: Claude Sonnet 5 |
|---|---|---|
| SQL Generation | 141 | 140 |
| Code Review | 144 | 144 |
| Code Completion | 132 | 118 |
| Code Refactoring | 146 | 146 |
| Bug Fixing | 148 | 148 |
| Unit Test Generation | 131 | 131 |
| Code Documentation | 136 | 135 |
| Regex Writing | 125 | 123 |
| CI/CD Pipelines | 127 | 127 |
| Frontend Component Design | 129 | 129 |
| Data Analysis | 133 | 133 |
| CSV / Spreadsheet Cleanup | 136 | 135 |
| ETL Scripting | 137 | 136 |
| JSON Extraction | 131 | 121 |
| Bulk Data Labeling | 128 | 118 |
| Long-Document Summarization | 147 | 146 |
| Short-Form Summarization | 126 | 116 |
| Blog Post Writing | 129 | 128 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →