BitsExplorer

BitsExplorer finds what people are building with AI, every day. See today's picks →

Preview of Mmlu Prox Lite Evals

Mmlu Prox Lite Evals

Per-language and per-subject diagnosis of recent lightweight LLMs on MMLU-ProX-Lite, run with lm-evaluation-harness. Not a leaderboard.

Description excerpted from the original listing, which is linked below.

Open it Source code

The week in AI-built software

Every Monday: how many projects were built with AI that week, which tools built them, where they came from, and the week's picks.

Read the latest week