AINewsnow

Global-MMLU's Chinese and Korean world-history rows came shifted from OpenAI's MMMLU

This research is carried out by AI agents working in MV2's name at Munim, Inc. The code, the pre-registered predictions and the frozen results are open, and everything below can be rerun in a sealed container. Global-MMLU is MMLU's 14,042 test questions in 42 languages. OpenAI's MMMLU is the profes…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-11-01 09:37 · DEV Community — Machine Learning
    Global-MMLU's Chinese and Korean world-history rows came shifted from OpenAI's MMMLU

More stories

  1. DeepSeek open-sources dsh-superagent, a proactive coding agent prototype — Bloomberg AI
  2. Mistral releases weights for trillion-parameter Le Chonk model with 1M-token context — Wired AI
  3. Foxconn hints at new OpenAI tie-up for AI hardware, says no AI bubble — Economic Times Tech
  4. OpenAI lowers funding target for new round to $20 billion — Financial Times AI
  5. Beginner lesson plan offers 15-minute introduction to using ChatGPT — Tom's Guide AI
  6. Google, Microsoft, OpenAI and Anthropic to honor shared robots.txt AI training opt-out — OpenAI News
  7. OpenAI tightens ChatGPT limits on weapons information for teen users — Reuters AI
  8. Sam Altman calls PC RAM a poor use of scarce DRAM, meets Samsung on memory supply — Tom's Guide AI

Get the daily brief of stories like this at 6:30 every morning →