I checked 30 frontier model cards. Here are the benchmarks labs report

·Hacker News··

An evidence-first daily map of new AI benchmarks, evaluations, and datasets.

Read full article →

Related Articles

ChatGPT lost 22 points of web share in a year
echohive42 · Hacker News · 5h ago
OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors
donsupreme · Hacker News · 3mo ago
Accelerating Gemma 4: faster inference with multi-token prediction drafters
amrrs · Hacker News · 3mo ago
A couple million lines of Haskell: Production engineering at Mercury
unignorant · Hacker News · 3mo ago
Using “underdrawings” for accurate text and numbers
samcollins · Hacker News · 3mo ago