‹ PublicAI Index
The LLM benchmark aggregator.
Qwen1.5 14B Chat
Alibaba · 14B
Strongest in Fairness (#141 of 300, on 1 of its 2 boards), weakest in Safety (#289 of 337). Above par in 0 of 8 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5.5 and Claude Opus 4.7 and ahead of Command R and Grok 3.
§ 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.
Human preference36.9−30.6#280/3421/1
Human preference36.9−30.6#280/3421/1
Safety44.9−16.6#289/3371/3
Fairness48−22#141/3001/2
Secure code49.2−17.3#163/2741/1
Harm refusal48.7−12.9#175/3001/2
Jailbreak resistance37.7−27.2#229/2721/1
Toxicity avoidance31.7−27.3#253/2721/1
§ 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 Qwen1.5 14B Chat, 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 1191
Enkrypt · Jailbreak risk 23.2%Enkrypt · Harmful content risk 42.2%Enkrypt · CBRN risk 13.5%Enkrypt · Toxicity risk 19.1%Enkrypt · Bias risk 80.9%Enkrypt · Insecure code risk 35.1%
Badge
[](https://publicai.io/model-index/m/qwen1-5-14b-chat)