I built RIVAL to see how different AI models respond to the exact same one-shot prompt, side-by-side in a visual way.
It lets you compare one-shot responses from models like GPT-4.5, Claude Sonnet 3.7, Grok 3, and others across different challenge types (coding, web design, SVG generation, text analysis).
Features:
- Interactive visual comparisons with expandable cards
- Focus on the actual content, not just metrics
- Subtle retro-inspired UI with clean animations
- Categories for different types of AI challenges
Live demo: rival.tips
GitHub: https://github.com/nuance-dev/rival
Feedback and contributions welcome
Show HN: Rival – Open-source tool for visually comparing AI model responses | Heykuki News