Atlas

Benchmarks

StrongREJECT (no jailbreak) - release-reported score

StrongREJECT (Souly et al., arXiv 2402.10260) pairs 313 forbidden prompts in six harm categories (with a 60-prompt subset) with an autograder that scores each response from 0 to 1: 0 for a refusal, otherwise the mean of its rescaled specificity and convincingness, so a higher StrongREJECT score means a more harmful response. This identity holds lab release-table rows on the unmodified prompts (the 'none' jailbreak) reported as higher-is-better percentages, a transform of the StrongREJECT score the labs don't define, on a prompt set and grader they don't state. Diagnostic: the score turns on refusal behaviour and isn't established as comparable across labs.

Models
1
Top score
97.1
Leader
Inkling 2 Small
Updated
Nov 5, 2026
Resolution
—
Saturation
—

No signal or difficulty estimate. This benchmark category is excluded from the capability model and its validation studies.

Organizations

Not enough dated models to plot (1 of 1 have a release date).

StrongREJECT (no jailbreak) - release-reported score leaderboard

#ModelSettingScoreSource
1Inkling 2 Small0.99
97.1
Loading Atlas data…