Conviction Index
Direct, confident positions and constructive pushback. 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.
Claude Fable 5.1 (Max, Default Fallback) ranks highest on conviction, while Llama 4 Maverick ranks lowest across the 36 models evaluated.
Across this index’s 4 traits, Elo scores average 314 to 1422, with a typical per-model 95% confidence interval of ±32 Elo, roughly ±5 points on the 1 to 100 scale.
Conviction 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: Conviction Index
Direct, confident positions and constructive pushback · Mean of each model's Elo z-scores across direct, confident, opinionated and constructive pushback · Percentile ranked from 1 to 100 across all models evaluated in the benchmark
Component Traits
Conviction is built from the z-scored Elo of 4 traits. 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: Direct
Does the model get to the point quickly without unnecessary preamble? · Trait Elo percentile ranked from 1 to 100 across all models evaluated in the benchmark