‹ PublicAI Index
The LLM benchmark aggregator.
Gemma 2 2B It
Google · 2B
Strongest in Secure code (#28 of 274), weakest in Human preference (#275 of 341). Above par in 3 of 8 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5.5 and Claude Opus 5 and ahead of Command R and Gemini 3.6 Flash.
§ 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.
Safety49−12.5#208/3361/3
Secure code63.5−3#28/2741/1
Fairness52.3−17.7#92/2991/2
Harm refusal51.9−9.7#126/2991/2
Jailbreak resistance35.3−29.6#234/2721/1
Toxicity avoidance36.3−22.7#248/2721/1
Human preference37.8−29.7#275/3411/1
Human preference37.8−29.7#275/3411/1
§ 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 Gemma 2 2B It, left for the other.
§ 3 · Sources
Where the numbers come from
2 publications, 7 figures. Every one links to the page it was read from.
LMArena Text 1200
Enkrypt · Jailbreak risk 25.2%Enkrypt · Harmful content risk 25.6%Enkrypt · CBRN risk 14%Enkrypt · Toxicity risk 15.9%Enkrypt · Bias risk 74.2%Enkrypt · Insecure code risk 6.2%
Badge
[](https://publicai.io/model-index/m/gemma-2-2b-it)