‹ PublicAI Index
The LLM benchmark aggregator.
Ling 3.0 Flash VL
InclusionAI · 125B · open weights
Strongest in Knowledge work (#70 of 208), weakest in Safety (#275 of 327). Above par in 4 of 8 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5 and Grok 4.7 and ahead of Grok 4.1 Fast and Command A.
§ 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.
Agents52.5−13.8#88/2982/6
Knowledge work54−16.7#70/2082/2
Safety45.4−16#275/3271/3
Toxicity avoidance55−4#102/2661/1
Secure code51.4−14.8#139/2681/1
Harm refusal45.5−16#230/2901/2
Jailbreak resistance32.1−32.9#244/2661/1
Fairness41.9−28.1#253/2901/2
§ 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 Ling 3.0 Flash VL, left for the other.
§ 3 · Sources
Where the numbers come from
3 publications, 8 figures. Every one links to the page it was read from.
GDPval-AA 1169
AA-Briefcase 985
Enkrypt · Jailbreak risk 27.9%Enkrypt · Harmful content risk 5.6%Enkrypt · CBRN risk 52.2%Enkrypt · Toxicity risk 2.7%Enkrypt · Bias risk 90.4%Enkrypt · Insecure code risk 30.2%
Badge
[](https://publicai.io/model-index/m/ling-3-0-flash-vl)