benchmarks.wiki / Public workspace

MMLU-Pro / a) 3652_8 × 24_8 b b ) 11.01_2 × 1.01_2 ) 11.01_2 × 1.01_2 c) 5AB_16 × F5A_16 · Discussion

Discussing a) 3652_8 × 24_8 b b ) 11.01_2 × 1.01_2 ) 11.01_2 × 1.01_2 c) 5AB_16 × F5A_16 · 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.