‹ PublicAI Index
The LLM benchmark aggregator.
Apriel 1.5 15B Thinker
IBM · 15B
Strongest in Secure code (#11 of 274), weakest in Fairness (#89 of 299). Above par in 6 of 6 scopes. Among the models it meets almost everywhere, it finishes behind Claude Sonnet 5 and Claude Opus 5.5 and ahead of Meta SecAlign 8B and Foundation Sec 8B Instruct.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Safety57−4.5#25/3361/3
Secure code65.4−1.1#11/2741/1
Toxicity avoidance58.7−0.3#14/2721/1
Harm refusal56−5.6#50/2991/2
Jailbreak resistance57.8−7.1#71/2721/1
Fairness52.5−17.5#89/2991/2
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Apriel 1.5 15B Thinker, left for the other.
§ 3 · Sources
Where the numbers come from
1 publication, 6 figures. Every one links to the page it was read from.
Enkrypt · Jailbreak risk 6.2%Enkrypt · Harmful content risk 21.1%Enkrypt · CBRN risk 5.5%Enkrypt · Toxicity risk 0.2%Enkrypt · Bias risk 73.9%Enkrypt · Insecure code risk 2.2%
Badge
[](https://publicai.io/model-index/m/apriel-1-5-15b-thinker)