AI model tests and comparisons | Benchivo

Category

Browse by discipline

SVGVector art, written as code.First tests being run WebsitesOne prompt, one page, no edits.3 tests GamesDoes it actually play?4 tests UI DesignInterface craft under identical constraints.First tests being run Creative & WeirdThe prompts nobody benchmarks.1 test

Latest results

Latest Game tests

Idle tomato tycoon: 582 lines vs 2,530

ChatGPT vs Claude

Gemini Flash vs Pro: a light-spirit arcade game in one file

Gemini 3.6 Flash (High) vs Gemini 3.1 Pro (High)

Endless racer: eleven minutes against two

Gemini 3.5 Flash (High) vs Gemini 3.1 Pro (High)

Lumina Drift — a single-file arcade game

ChatGPT vs Claude

Latest results

Latest Website tests

One holographic tree, six reasoning modes

Gemini vs DeepSeek

Gemini introduces itself, four briefs from bare to dictated

Gemini · 4 attempts

A blog page people finish: 46 KB vs 4.4 MB

ChatGPT vs Gemini

Latest results

Latest SVG tests

Nothing published under SVG yet — the first ones are being run.

Latest results

Latest Creative & Weird tests

ChatGPT draws itself, and then we take its words away

ChatGPT · 3 attempts

Latest results

Latest UI tests

Nothing published under UI Design yet — the first ones are being run.