‹ PublicAI IndexGoogle
The LLM benchmark aggregator.
Gemini 4 Carbon
Strongest in Human preference (#1 of 354), weakest in Professional (#28 of 194). Above par in 12 of 12 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5.2 and Muse Wonder Full and ahead of Muse Wonder and GPT-6.1 Sol.
§ 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 preference68.8leads#1/3541/1
Human preference68.8leads#1/3541/1
Core abilities61.9−3.4#6/1991/4
General intelligence67.1−2.3#7/1781/3
Reasoning62.7−2.7#8/1952/5
Reasoning68.4−0.6#2/1472/3
Agents60.7−5.7#10/2982/6
Knowledge work67.1−3.6#10/2082/2
Coding56.3−9.9#27/1791/6
Agentic coding56.9−10#25/1731/5
Professional55.6−6.8#28/1941/2
Legal61.3−4.6#8/1731/1
§ 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 Gemini 4 Carbon, left for the other.
§ 3 · Sources
Where the numbers come from
7 publications, 9 figures. Every one links to the page it was read from.
LMArena Text 1526
Artificial Analysis Intelligence Index 60
GDPval-AA 1733
AA-Briefcase 1611
ARC-AGI-2 92.1%
SimpleBench 92.6%
Vals · Legal Research Bench 55.77%Vals · Harvey Legal Agent Benchmark 17.5%Vals · Vibe Code Bench 89.06% (OpenHands)
Badge
[](https://publicai.io/model-index/m/gemini-4-carbon)