AILenny's Newsletterabout 3 hours ago
Sonnet 5 tested against 4 frontier models
2 min read
Claire Vo built the How I AI Bench eval harness using Claude Code and ran Sonnet 5 blind against Sonnet 4.6, Opus 4.8, GPT-5.5, and Gemini 3 Pro across 64 generations. The benchmark scored PRD quality, prototype generation, agentic task completion, and agent personality using 70% human vibe scoring and 30% LLM as judge.
Level
Hype check
Tap to vote and see what everyone thinks.
