benchgap
xAI · model

Grok 4 Fast (Reasoning) benchmark scores

As of 2026-11-22, Grok 4 Fast (Reasoning) (xAI) has measured scores on 18 benchmarks and estimated scores on 71 more.

BenchmarkScoreSource
AA-GPQA Diamond84.7%measured
AA-HLE19.1%measured
AA-SciCode45.2%estimated ± 3.8 pp, medium confidence
Artificial Analysis Intelligence Index17.9%measured
CritPt2.9%measured
GDPval-AA4.9%estimated ± 11.0 pp, low confidence
GPQA Diamond88.3%estimated ± 1.8 pp, high confidence
HLE22.7%estimated ± 8.5 pp, medium confidence
IFBench56.0%estimated ± 6.6 pp, medium confidence
AA-LCR73.7%measured
LiveCodeBench v686.0%estimated ± 2.2 pp, medium confidence
AA-Omniscience Accuracy22.8%measured
BrowseComp60.0%estimated ± 13.0 pp, low confidence
IFEval91.2%estimated ± 2.8 pp, high confidence
LongBench v260.8%estimated ± 5.5 pp, medium confidence
τ²-bench results65.8%measured
AA Coding Index22.6%estimated ± 5.6 pp, medium confidence
AA-MMMU-Pro61.8%measured
APEX-Agents-AA1.6%estimated ± 11.4 pp, low confidence
BioMysteryBench (human-difficult)30.5%estimated ± 6.8 pp, low confidence
SWE-bench Verified64.1%estimated ± 4.4 pp, medium confidence
BFCL v453.4%estimated ± 8.5 pp, low confidence
SWE-bench Pro53.0%estimated ± 2.9 pp, low confidence
AA Agentic Index14.4%estimated ± 12.7 pp, low confidence
MMLU-Pro81.7%estimated ± 4.8 pp, high confidence
AA-IFBench50.5%measured
FailureSensorIQ64.1%measured
GPQA87.2%estimated ± 4.5 pp, high confidence
MMLU90.4%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond85.4%measured
Vals LiveCodeBench79.0%measured
Vals MMLU-Pro79.7%measured
MMMLU87.6%estimated ± 0.7 pp, medium confidence
MMMU74.4%estimated ± 2.7 pp, high confidence
AA MMLU-Pro85.0%measured
ARC-AGI-178.8%estimated ± 6.5 pp, medium confidence
ARC-AGI-239.2%estimated ± 13.8 pp, low confidence
CursorBench 3.259.1%estimated ± 7.2 pp, low confidence
FrontierCode 1.1 Main29.3%estimated ± 6.2 pp, low confidence
Mystery Game Puzzles7.3%estimated ± 4.7 pp, medium confidence
ParseBench-147.3%estimated ± 6.2 pp, medium confidence
Vals SWE-bench45.4%measured
VulcanBench v380.5%estimated ± 5.6 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)51.3%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)31.0%estimated ± 0.8 pp, low confidence
CursorBench 4.036.0%estimated ± 4.5 pp, medium confidence
HLE w/o tools24.7%estimated ± 4.9 pp, high confidence
PostTrainBench v1.119.9%estimated ± 10.5 pp, low confidence
ARC-AGI-31.3%estimated ± 9.8 pp, medium confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
BinaryAudit21.2%estimated ± 8.9 pp, low confidence
CompileBench55.6%measured
OTelBench21.4%estimated ± 7.7 pp, low confidence
Vibe Code Bench0.0%measured
ParseBench-248.1%estimated ± 6.2 pp, medium confidence
CharXiv71.8%estimated ± 6.3 pp, low confidence
CharXiv w/o tools71.1%estimated ± 2.5 pp, medium confidence
AI2D_TEST88.0%estimated ± 2.0 pp, medium confidence
C-Eval90.9%estimated ± 1.0 pp, medium confidence
ERQA41.2%estimated ± 3.1 pp, medium confidence
MathVision60.7%estimated ± 3.1 pp, medium confidence
MMLU-Redux93.9%estimated ± 0.8 pp, medium confidence
MMMU-Pro63.0%estimated ± 1.5 pp, high confidence
NL2Repo35.6%estimated ± 4.7 pp, medium confidence
PostTrainBench v119.0%estimated ± 3.1 pp, low confidence
ScreenSpot Pro65.7%estimated ± 10.8 pp, low confidence
SuperGPQA65.2%estimated ± 9.3 pp, medium confidence
Video-MME (w/o subtitle)75.3%estimated ± 1.7 pp, medium confidence
AA LiveCodeBench83.2%measured
HealthBench Hard18.8%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)6.2%estimated ± 6.5 pp, low confidence
MMLU-Pro (Arcee)88.0%estimated ± 4.0 pp, medium confidence
React Native Evals0.0%estimated ± 3.0 pp, low confidence
SWE-Rebench0.0%estimated ± 6.5 pp, low confidence
PostTrainBench17.0%estimated ± 8.3 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (raw)26.6%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)45.6%estimated ± 3.4 pp, low confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)38.7%estimated ± 4.5 pp, medium confidence
HLE-Verified1.0%estimated ± 4.6 pp, low confidence
LABBench278.7%estimated ± 1.9 pp, low confidence
STEMBench2.4%estimated ± 0.2 pp, low confidence
SimpleQA22.0%estimated ± 4.3 pp, medium confidence
OpenHarmony Bench v1.043.4%estimated ± 3.2 pp, medium confidence
MRCRv282.9%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.1%estimated ± 2.6 pp, low confidence
BioBasicsBench34.1%estimated ± 3.8 pp, low confidence
MMMU-Pro w/ Python66.4%estimated ± 2.0 pp, medium confidence