OpenAI highlights GPT-5 scores on math, coding, and health benchmarks: 94.6% on AIME 2025 without tools, 74.9% on SWE-bench Verified, 46.2% on HealthBench Hard (Carl Franzen/VentureBeat)

Carl Franzen / VentureBeat:
OpenAI highlights GPT-5 scores on math, coding, and health benchmarks: 94.6% on AIME 2025 without tools, 74.9% on SWE-bench Verified, 46.2% on HealthBench Hard  —  After literally years of hype and speculation, OpenAI has officially launched a new lineup of large language models (LLMs) …

from Techmeme https://ift.tt/4asQR1i