Slop Index
Use of filler and generic language. The index z-scores each component trait’s Elo across all models evaluated in the benchmark, calculates the mean with inverted traits entering negatively, and percentile ranks the result from 1 to 100.
Component traits:Slop
Llama 4 Maverick ranks highest on slop, while GPT-6 Sol (Max) ranks lowest across the 36 models evaluated.
Across this index’s 1 trait, Elo scores average 611 to 2303, with a typical per-model 95% confidence interval of ±42 Elo, roughly ±3 points on the 1 to 100 scale.
Slop Leaderboard
The mean of each model’s trait Elo z-scores, percentile ranked from 1 to 100 across all models evaluated in the benchmark. Whiskers show each model’s 95% confidence interval.
AA-PersonalityBench: Slop Index
Use of filler and generic language · Mean of each model's Elo z-scores across slop · Percentile ranked from 1 to 100 across all models evaluated in the benchmark
Component Traits
Slop is built from the z-scored Elo of 1 trait. Open any trait for its full leaderboard.
Trait Leaderboards
Each component trait’s Elo percentile ranked from 1 to 100 across all models evaluated in the benchmark.
AA-PersonalityBench: Slop
How much generic filler or AI-flavored padding could be removed without losing substance? · Trait Elo percentile ranked from 1 to 100 across all models evaluated in the benchmark