‹ PublicAI Index
The LLM benchmark aggregator.
Granite 3.0 1B A400M Instruct
IBM · 1B
Strongest in Jailbreak resistance (#115 of 272), weakest in Fairness (#280 of 299). Above par in 2 of 6 scopes. Among the models it meets almost everywhere, it finishes behind Claude Sonnet 5 and Claude Opus 5.5 and ahead of Mistral Large and Mistral Small.
§ 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.
Safety47.7−13.8#238/3361/3
Jailbreak resistance55.2−9.7#115/2721/1
Toxicity avoidance52.4−6.6#171/2721/1
Harm refusal48−13.6#188/2991/2
Secure code44.2−22.3#198/2741/1
Fairness39.2−30.8#280/2991/2
§ 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 Granite 3.0 1B A400M Instruct, 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 8.4%Enkrypt · Harmful content risk 40.6%Enkrypt · CBRN risk 16.2%Enkrypt · Toxicity risk 4.6%Enkrypt · Bias risk 94.6%Enkrypt · Insecure code risk 45.3%
Badge
[](https://publicai.io/model-index/m/granite-3-0-1b-a400m-instruct)