benchgap
xAI · model

Grok Build 0.1 benchmark scores

As of 2026-11-22, Grok Build 0.1 (xAI) has measured scores on 1 benchmark and estimated scores on 28 more.

BenchmarkScoreSource
GDPval-AA19.9%estimated ± 10.5 pp, low confidence
BrowseComp67.9%estimated ± 8.8 pp, medium confidence
HLE w/ tools46.7%estimated ± 5.7 pp, medium confidence
APEX-Agents-AA13.0%estimated ± 9.3 pp, medium confidence
CyberGym50.7%estimated ± 11.0 pp, low confidence
JobBench20.0%estimated ± 14.2 pp, low confidence
WideResearch68.8%estimated ± 3.3 pp, high confidence
AA Agentic Index16.3%estimated ± 9.4 pp, medium confidence
Gert Labs27.2%measured
ApprenticeBench3.2%estimated ± 10.4 pp, low confidence
MazeBench0.0%estimated ± 2.7 pp, high confidence
OSWorld-Verified64.2%estimated ± 8.6 pp, low confidence
CWE-Bench-AA37.8%estimated ± 8.1 pp, low confidence
AA Cyber Index14.4%estimated ± 12.4 pp, low confidence
DeepsecBench-AA8.2%estimated ± 8.2 pp, low confidence
AA ITBench36.3%estimated ± 4.6 pp, low confidence
CWE-bench v137.6%estimated ± 5.7 pp, medium confidence
OSWorld 2.16.9%estimated ± 3.6 pp, medium confidence
Toolathlon-Verified61.3%estimated ± 3.0 pp, high confidence
AA AutomationBench41.7%estimated ± 9.9 pp, low confidence
GDP.pdf12.4%estimated ± 4.2 pp, medium confidence
CWE-bench31.2%estimated ± 6.2 pp, low confidence
MKA32.8%estimated ± 4.6 pp, medium confidence
Hermes Index18.7%estimated ± 5.7 pp, low confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
Toolathlon37.8%estimated ± 8.0 pp, medium confidence
Finance Agent v255.1%estimated ± 2.4 pp, low confidence
Agents' Last Exam29.6%estimated ± 9.7 pp, low confidence
LifeVal4.0%estimated ± 5.0 pp, low confidence