HackerTrans
TopNewTrendsCommentsPastAskShowJobs

Data Viz: Mapping Model Performance on Reasoning vs. Honesty Benchmarks(claude.ai)

1 points·by lout332·10 mesi fa·1 comments
claude.ai
Data Viz: Mapping Model Performance on Reasoning vs. Honesty Benchmarks

https://claude.ai/public/artifacts/068899b8-19fc-4927-8561-736a075c5018

1 comments

lout332·10 mesi fa
Was curious about how different model families scale, so I plotted their HLE (reasoning) vs. MASK (honesty) scores. Found some interesting patterns, especially with the Claude and Gemini series. Might be relevant for those thinking about model reliability and robustness. Here's the data...