benchgap
xAI · model

Grok 4.1 Fast (Reasoning) benchmark scores

As of 2026-11-22, Grok 4.1 Fast (Reasoning) (xAI) has measured scores on 18 benchmarks and estimated scores on 86 more.

BenchmarkScoreSource
AA-GPQA Diamond85.3%measured
AA-HLE19.3%measured
AA-SciCode45.4%estimated ± 3.8 pp, high confidence
Artificial Analysis Intelligence Index20.4%measured
CritPt2.9%measured
GDPval-AA27.0%estimated ± 11.0 pp, low confidence
GPQA Diamond87.6%estimated ± 1.8 pp, high confidence
HLE22.8%estimated ± 8.5 pp, medium confidence
IFBench56.7%estimated ± 6.6 pp, medium confidence
AA-LCR74.0%measured
LiveCodeBench v686.7%estimated ± 2.2 pp, medium confidence
AA-Omniscience Accuracy25.1%measured
SciCode38.0%estimated ± 2.9 pp, low confidence
BrowseComp72.2%estimated ± 13.0 pp, low confidence
HLE w/ tools48.5%estimated ± 5.5 pp, medium confidence
IFEval91.5%estimated ± 2.8 pp, high confidence
LongBench v261.0%estimated ± 5.5 pp, medium confidence
τ²-bench results93.3%measured
AA Coding Index20.6%estimated ± 5.6 pp, medium confidence
AA-MMMU-Pro63.3%measured
APEX-Agents-AA25.5%estimated ± 11.4 pp, low confidence
BioMysteryBench (human-difficult)30.5%estimated ± 6.8 pp, low confidence
SWE-bench Verified62.0%estimated ± 4.4 pp, medium confidence
BFCL v468.1%estimated ± 8.5 pp, low confidence
SWE-bench Pro53.1%estimated ± 2.9 pp, low confidence
AA Agentic Index24.1%estimated ± 12.7 pp, low confidence
MMLU-Pro84.4%estimated ± 4.8 pp, high confidence
AA-IFBench52.7%measured
FailureSensorIQ64.6%measured
GPQA86.2%estimated ± 4.5 pp, high confidence
MMLU90.5%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond84.3%measured
Vals LiveCodeBench80.6%measured
Vals MMLU-Pro84.2%measured
MMMLU87.6%estimated ± 0.7 pp, medium confidence
MMMU75.5%estimated ± 2.7 pp, high confidence
Chess Puzzles45.3%estimated ± 12.3 pp, low confidence
AA MMLU-Pro85.4%measured
ARC-AGI-176.7%estimated ± 6.5 pp, medium confidence
ARC-AGI-234.3%estimated ± 13.8 pp, low confidence
CursorBench 3.259.1%estimated ± 7.2 pp, low confidence
FrontierCode 1.1 Main32.0%estimated ± 6.2 pp, low confidence
Mystery Game Puzzles42.0%estimated ± 14.6 pp, low confidence
NYT Connections87.4%measured
ParseBench-148.3%estimated ± 6.2 pp, medium confidence
Vals SWE-bench41.4%measured
VulcanBench v381.2%estimated ± 5.6 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)52.0%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)31.0%estimated ± 0.8 pp, low confidence
CursorBench 4.037.5%estimated ± 4.5 pp, high confidence
HLE w/o tools28.5%estimated ± 4.9 pp, high confidence
PostTrainBench v1.119.9%estimated ± 10.5 pp, low confidence
SpireClimb5.8%estimated ± 7.2 pp, medium confidence
StealthMark58.3%estimated ± 10.7 pp, low confidence
ARC-AGI-30.0%estimated ± 8.6 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
SkillsBench official leaderboard (BenchFlow)55.2%estimated ± 6.1 pp, medium confidence
BinaryAudit23.2%estimated ± 8.9 pp, low confidence
OTelBench22.5%estimated ± 6.6 pp, medium confidence
Vibe Code Bench1.2%measured
FACTS Multimodal49.0%estimated ± 4.0 pp, high confidence
ParseBench-249.8%estimated ± 6.2 pp, medium confidence
CharXiv72.9%estimated ± 6.3 pp, low confidence
CharXiv w/o tools72.2%estimated ± 2.5 pp, medium confidence
AI2D_TEST88.0%estimated ± 2.0 pp, medium confidence
C-Eval91.7%estimated ± 1.0 pp, medium confidence
CountBench86.5%estimated ± 2.9 pp, low confidence
DynaMath1.0%estimated ± 3.0 pp, low confidence
ERQA41.2%estimated ± 3.1 pp, medium confidence
MathVision64.3%estimated ± 3.1 pp, medium confidence
MMLU-Redux94.1%estimated ± 0.8 pp, medium confidence
MMMU-Pro64.6%estimated ± 1.5 pp, high confidence
NL2Repo35.4%estimated ± 4.7 pp, medium confidence
PostTrainBench v119.0%estimated ± 3.1 pp, low confidence
RealWorldQA74.9%estimated ± 2.9 pp, low confidence
ScreenSpot Pro66.7%estimated ± 10.8 pp, low confidence
SuperGPQA65.8%estimated ± 9.3 pp, medium confidence
V*0.0%estimated ± 7.5 pp, low confidence
Video-MME (w/o subtitle)76.0%estimated ± 1.7 pp, medium confidence
Video-MME (with subtitle)76.9%estimated ± 3.7 pp, low confidence
AA LiveCodeBench82.2%measured
HealthBench Hard18.8%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)10.3%estimated ± 6.5 pp, low confidence
MMLU-Pro (Arcee)88.0%estimated ± 4.0 pp, medium confidence
React Native Evals13.2%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)26.9%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)45.7%estimated ± 3.4 pp, low confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)39.0%estimated ± 4.5 pp, medium confidence
HLE-Verified0.3%estimated ± 4.6 pp, low confidence
LABBench279.9%estimated ± 1.8 pp, low confidence
BlenderWorld (text-only)80.7%estimated ± 4.3 pp, medium confidence
Cookie-Bench88.5%estimated ± 4.8 pp, medium confidence
STEMBench2.4%estimated ± 0.2 pp, low confidence
SimpleQA25.1%estimated ± 4.3 pp, medium confidence
OpenHarmony Bench v1.042.2%estimated ± 3.2 pp, medium confidence
MRCRv283.3%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/ Python67.7%estimated ± 2.0 pp, medium confidence
ExploitBench Internal Port13.4%estimated ± 13.8 pp, low confidence