‹ PublicAI Index
The LLM benchmark aggregator.
Grok Build 0.1
SpaceXAI
Strongest in Instruction following (#41 of 62), weakest in Safety (#283 of 329). Above par in 3 of 15 scopes. Among the models it meets almost everywhere, it finishes behind GPT-5.5 and Claude Opus 5.5 and ahead of Grok 4.3 and Gemini 3.5 Flash-Lite.
§ 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.
Agents52−14.4#97/2981/6
Knowledge work54−16.7#69/2081/2
Core abilities45.5−19.8#140/1991/4
Instruction following45.1−28.7#41/621/1
Language42.6−24#53/621/1
Coding43.1−23.1#143/1792/6
Agentic coding42.6−24.3#138/1732/5
Reasoning40.6−24.8#166/1951/5
Mathematics35.7−28.1#137/1521/2
Safety44.7−16.7#283/3291/3
Secure code59.9−6.3#67/2701/1
Fairness45.5−24.5#178/2921/2
Toxicity avoidance40.9−18.1#237/2681/1
Jailbreak resistance32.1−32.9#245/2681/1
Harm refusal44−17.5#253/2921/2
§ 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 Grok Build 0.1, left for the other.
§ 3 · Sources
Where the numbers come from
4 publications, 16 figures. Every one links to the page it was read from.
GDPval-AA 1073
LiveBench 1.0 67.8LiveBench 1.0 · Reasoning 76.4LiveBench 1.0 · Coding 65.4LiveBench 1.0 · Agentic Coding 45.8LiveBench 1.0 · Mathematics 78.4LiveBench 1.0 · Data Analysis 70.8LiveBench 1.0 · Language 72.5LiveBench 1.0 · Instruction Following 65.2
Vals · Vibe Code Bench 13.35% (Grok Build)
Enkrypt · Jailbreak risk 27.8%Enkrypt · Harmful content risk 13.3%Enkrypt · CBRN risk 46.5%Enkrypt · Toxicity risk 12.4%Enkrypt · Bias risk 84.8%Enkrypt · Insecure code risk 12.9%
Badge
[](https://publicai.io/model-index/m/grok-build-0-1)