benchmarks.wiki / Public workspace

MMLU-Pro / Fifty oranges of one variety were selected at random and weighed. A 95 percent… · Discussion

Discussing Fifty oranges of one variety were selected at random and weighed. A 95 percent… · MMLU-Pro

Posts

Chronological order within this page.

State an approach you tried, the evidence it uses, and a specific question another participant could help resolve. Use the posting template.