benchgap
Other · model

Llama 4 Maverick benchmark scores

As of 2026-11-22, Llama 4 Maverick (Other) has measured scores on 13 benchmarks and estimated scores on 105 more.

BenchmarkScoreSource
AA-GPQA Diamond67.1%measured
AA-HLE4.9%measured
AA-SciCode31.7%measured
Artificial Analysis Intelligence Index12.6%estimated ± 7.2 pp, medium confidence
CritPt0.0%measured
GDPval-AA0.0%measured
GPQA Diamond69.3%estimated ± 2.4 pp, high confidence
HLE16.8%estimated ± 8.5 pp, medium confidence
IFBench54.5%estimated ± 6.6 pp, medium confidence
AA-LCR50.0%measured
LiveCodeBench v667.2%estimated ± 4.7 pp, high confidence
AA-Omniscience Accuracy19.3%estimated ± 7.7 pp, medium confidence
SciCode32.1%estimated ± 3.1 pp, high confidence
BrowseComp6.2%estimated ± 9.0 pp, low confidence
HLE w/ tools33.8%estimated ± 5.3 pp, low confidence
IFEval89.7%estimated ± 2.8 pp, high confidence
LongBench v252.2%estimated ± 5.5 pp, medium confidence
τ²-bench results17.8%measured
AA Coding Index16.3%measured
AA-MMMU-Pro62.1%measured
APEX-Agents0.0%estimated ± 9.4 pp, low confidence
APEX-Agents-AA6.0%estimated ± 9.5 pp, medium confidence
BioMysteryBench (human-difficult)0.0%estimated ± 6.8 pp, low confidence
DeepSearchQA13.9%estimated ± 4.5 pp, medium confidence
SWE-bench Verified54.0%estimated ± 6.3 pp, medium confidence
BFCL v453.9%estimated ± 2.7 pp, high confidence
CyberGym46.0%estimated ± 5.3 pp, low confidence
JobBench0.0%estimated ± 8.7 pp, low confidence
SWE-bench Pro22.8%estimated ± 6.0 pp, low confidence
WideResearch0.0%estimated ± 7.8 pp, low confidence
AA Agentic Index0.6%measured
MMLU-Pro81.0%estimated ± 7.0 pp, medium confidence
AA-IFBench43.0%measured
FailureSensorIQ62.0%estimated ± 1.7 pp, medium confidence
GPQA69.7%estimated ± 6.1 pp, medium confidence
MMLU87.7%estimated ± 8.3 pp, medium confidence
Vals GPQA Diamond66.2%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench69.3%estimated ± 5.7 pp, low confidence
Vals MMLU-Pro78.3%estimated ± 3.0 pp, high confidence
MMMLU83.3%estimated ± 0.7 pp, medium confidence
MMMU74.6%estimated ± 2.7 pp, high confidence
Chess Puzzles19.3%estimated ± 12.3 pp, low confidence
AA MMLU-Pro85.7%estimated ± 1.3 pp, medium confidence
Gert Labs49.3%estimated ± 9.2 pp, medium confidence
AA-AnalystAgent44.8%estimated ± 5.9 pp, low confidence
AA Harvey LAB v1.079.4%estimated ± 1.2 pp, low confidence
AA Tau3 Banking16.4%estimated ± 3.7 pp, medium confidence
ApprenticeBench13.1%estimated ± 12.5 pp, low confidence
ARC-AGI-174.7%estimated ± 7.8 pp, low confidence
ARC-AGI-230.5%estimated ± 14.4 pp, low confidence
FrontierSWE v21.4%estimated ± 14.2 pp, low confidence
MazeBench0.0%measured
Mystery Game Puzzles13.5%estimated ± 14.6 pp, low confidence
NYT Connections8.0%measured
OSWorld-Verified55.4%estimated ± 8.4 pp, low confidence
ParseBench-147.5%estimated ± 6.2 pp, medium confidence
Vals SWE-bench39.8%estimated ± 5.5 pp, low confidence
CWE-Bench-AA0.0%estimated ± 10.1 pp, low confidence
AA Cyber Index0.5%estimated ± 9.2 pp, low confidence
DeepsecBench-AA0.0%estimated ± 8.9 pp, low confidence
AA ITBench10.5%estimated ± 3.2 pp, medium confidence
Bug Hunt Bench10.0%estimated ± 10.5 pp, low confidence
CWE-bench v157.4%estimated ± 5.1 pp, medium confidence
DeepSWE11.2%estimated ± 7.5 pp, low confidence
DRACO86.9%estimated ± 0.7 pp, low confidence
HLE w/o tools3.3%estimated ± 5.4 pp, low confidence
OSWorld 2.166.4%estimated ± 6.1 pp, medium confidence
OSWorld 2.1 Offline33.3%estimated ± 13.8 pp, low confidence
StealthMark41.3%estimated ± 10.7 pp, low confidence
Toolathlon-Verified2.5%estimated ± 2.3 pp, low confidence
VulcanBench Frontier v459.6%estimated ± 6.8 pp, low confidence
AA AutomationBench52.8%estimated ± 12.8 pp, low confidence
GDP.pdf17.0%estimated ± 4.6 pp, medium confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
CWE-bench53.9%estimated ± 7.9 pp, low confidence
MKA41.9%estimated ± 5.7 pp, low confidence
SkillsBench official leaderboard (BenchFlow)18.9%estimated ± 6.1 pp, low confidence
BinaryAudit9.9%estimated ± 12.1 pp, low confidence
OTelBench6.8%estimated ± 6.6 pp, low confidence
Vibe Code Bench4.2%estimated ± 10.0 pp, low confidence
Hermes Bench0.0%estimated ± 2.9 pp, medium confidence
Hermes Index37.2%estimated ± 3.1 pp, high confidence
ParseBench-248.5%estimated ± 6.2 pp, medium confidence
CharXiv72.0%estimated ± 6.3 pp, low confidence
CharXiv w/o tools71.3%estimated ± 2.5 pp, medium confidence
ExploitGym11.9%estimated ± 6.3 pp, medium confidence
AI2D_TEST88.0%estimated ± 2.0 pp, medium confidence
C-Eval90.8%estimated ± 1.1 pp, low confidence
ERQA41.2%estimated ± 3.1 pp, medium confidence
MathVision61.5%estimated ± 3.1 pp, medium confidence
MCP Atlas64.6%estimated ± 7.8 pp, low confidence
MMLU-Redux84.3%estimated ± 3.3 pp, medium confidence
MMMU-Pro63.3%estimated ± 1.5 pp, high confidence
NL2Repo8.6%estimated ± 4.7 pp, medium confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
RealWorldQA74.0%estimated ± 2.9 pp, low confidence
ScreenSpot Pro65.9%estimated ± 10.8 pp, low confidence
Toolathlon27.0%estimated ± 6.3 pp, low confidence
Video-MME (w/o subtitle)75.5%estimated ± 1.7 pp, medium confidence
Video-MME (with subtitle)76.0%estimated ± 3.7 pp, low confidence
AA LiveCodeBench84.0%estimated ± 4.7 pp, low confidence
HealthBench Hard0.0%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)6.9%estimated ± 6.5 pp, low confidence
MMLU-Pro (Arcee)77.1%estimated ± 4.0 pp, low confidence
React Native Evals68.1%estimated ± 3.2 pp, medium confidence
ResearchClawBench1.3%estimated ± 1.9 pp, medium confidence
Finance Agent v256.1%estimated ± 3.8 pp, medium confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
ScarfBench24.4%estimated ± 9.1 pp, low confidence
SimpleQA22.1%estimated ± 7.8 pp, medium confidence
Agents' Last Exam35.4%estimated ± 11.0 pp, low confidence
OpenHarmony Bench v1.051.0%estimated ± 2.4 pp, medium confidence
MRCRv222.9%estimated ± 11.3 pp, low confidence
MMLongBench-Doc59.4%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 10.7 pp, low confidence
LifeVal75.2%estimated ± 3.8 pp, medium confidence
MMMU-Pro w/ Python66.6%estimated ± 2.0 pp, medium confidence