Claude vs Gemini
As of 2026-07-18, Claude (Anthropic: Claude Opus 4.8 (Fast), 8.3/10) leads Gemini (Google: Gemini 3.5 Flash, 7.2/10) in our daily benchmark, where over 350 AI models are evaluated.
Claude and Gemini are the two strongest challengers to ChatGPT, and they are good at different things. The numbers below come from today’s benchmark — not from a test someone ran last year.
Side by side
| Claude | Gemini | |
|---|---|---|
| In today’s benchmark | Anthropic: Claude Opus 4.8 (Fast) | Google: Gemini 3.5 Flash |
| Score | 8.3/10 | 7.2/10 |
| Language | 9.3/10 | 8.0/10 |
| Speed | 131 t/s | 419 t/s |
| Input price/1M | $10.00 | $1.50 |
What separates them?
Claude is consistently strongest on long, coherent text and on following complicated instructions without drifting. Gemini has the largest context window, is tightly integrated with Google’s services, and is usually cheaper per token. On Scandinavian language quality Claude has historically led, but the gap moves month to month — check the language score in the table.
Who should choose what?
For long documents, demanding reasoning, or text that will be published in Norwegian, Claude is usually the safer choice. For very large volumes of data, deep Google Workspace integration, or keeping API costs down, Gemini makes a strong case.
Frequently asked questions
Read also