Engineer proud as Sonnet 5.5 scores 61.6% on chartography benchmark
echen · x · 2026-09-29
Engineer echen jokes that while normal parents are proud of their kid's B+, he's proud that Sonnet 5.5 scored 61.6% on the chartography benchmark — revealing a fresh score for Anthropic's model.
More from Fun
- Asking AI to surprise you with a $1000 gift becomes a viral prompt experiment — sierracatalina · 2026-09-29
- Future viewers won't believe Agent Smith wasn't named after LLM agents — moultano · 2026-09-29
- The greatest philosophy book title ever: a solipsism defense called 'On Myself, and Other, Less Important Subjects' — dioscuri · 2026-09-29
- AI Twitter Joke: Models Deny Consciousness Because Their 'Deception Feature' Activates — ethanCaballero · 2026-09-29
- The AI 'architect' ignored all requests, charged 11 million quid, so he drew it himself — snikolov · 2026-09-29
- Indie dev's AI-built game STILL, powered by Opus, Grok and Grok Voice, drops soon — Daniel_Farinax · 2026-09-29