A benchmark joke says Anthropic doing badly is the fastest way to lose trust in it
teortaxesTex · x · 2026-07-25
A joking post says the easiest way to undermine Lisan’s trust in any benchmark is to show Anthropic doing badly on it.
The attached screenshot shows a discussion around Opus 5 ECI: one user claims it should be around 163.5 based on public benchmarks, says Anthropic’s internal AECl is 162.1, and notes that it is higher than Mythos 5. The punchline is the complaint that public benchmarks should be harder because the current ones are too easy to game or over-interpret.
Related event: Anthropic's Benchmark Scores Spark Community Trust Crisis(2 posts)→
More from Fun
- LisanBench goes viral in China: flood of requests surprises its creator — scaling01 · 2026-10-27
- Ask an LLM for 10 bold 2030 AI predictions — many already happened — FlorianGallwitz · 2026-10-27
- Dev hits back at AI-game backlash: same video praised if posted without the AI label — AIandDesign · 2026-10-27
- The Keynote Dilemma: Broadly Applicable vs. Actually Deep at ML Confs — m2saxon · 2026-10-27
- Meme: 'Hello World' then vs now — from DOS terminal to ChatGPT — astralmatrix · 2026-10-27
- Dev vents: 'I legitimately hate the way Claude speaks' — TejasKumar_ · 2026-10-27