Claude Sonnet 5 vs Gemini 3.1 Pro
Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-07-01.
Cost at a Glance
Gemini 3.1 Pro is 1.1× more expensive than Claude Sonnet 5 (11.8% savings if you switch).
At 5M input + 2M output tokens per month:
Choosing Claude Sonnet 5 could save you $4.00/mo
Price Comparison (per 1M tokens)
| Metric | Claude Sonnet 5 | Gemini 3.1 Pro |
|---|---|---|
| Input (per 1M tokens) | $2.00 | $2.00 |
| Output (per 1M tokens) | $10.00 | $12.00 |
| Cache Write (per 1M tokens) | $2.50 | — |
| Cache Read (per 1M tokens) | $0.20 | $0.20 |
| Batch Input (per 1M tokens) | $1.00 | — |
| Batch Output (per 1M tokens) | $5.00 | — |
Prices are per 1 million tokens. Actual costs depend on your monthly token volume. Use the calculator →
Specifications
| Spec | Claude Sonnet 5 | Gemini 3.1 Pro |
|---|---|---|
| Context Window | 1M | 1M |
| Max Output Tokens | 128K | 64K |
| Knowledge Cutoff | 2026-01 | 2026-04 |
| Modalities | Text, Image | Text, Image, Audio, Video |
| Prompt Caching | Yes | Yes |
| Batch API | Yes | No |
| Thinking / Reasoning | Yes | Yes |
Benchmark Scores
| Benchmark | Claude Sonnet 5 | Gemini 3.1 Pro |
|---|---|---|
| SWE-bench Verified | 82.1 | 80.6 |
| MMLU-Pro | 86.5 | 86.5 |
| HumanEval | 94.8 | 93.5 |
Benchmark scores from official provider reports. Higher is better. Missing scores indicate the provider has not published that benchmark yet.
Use Cases
Claude Sonnet 5
Gemini 3.1 Pro
About the Providers
Claude Sonnet 5 is developed by Anthropic. Gemini 3.1 Pro is developed by Google. This is a cross-provider comparison between Anthropic and Google models. For the most up-to-date pricing, always check the official API documentation from each provider.