benchgap
Anthropic · model

Claude 4 Sonnet benchmark scores

As of 2026-11-22, Claude 4 Sonnet (Anthropic) has measured scores on 13 benchmarks and estimated scores on 103 more.

BenchmarkScoreSource
AA-GPQA Diamond68.3%measured
AA-HLE4.3%measured
AA-SciCode45.0%estimated ± 3.8 pp, high confidence
AIME2637.6%estimated ± 4.3 pp, low confidence
Artificial Analysis Intelligence Index16.6%measured
CritPt1.1%measured
GDPval-AA26.1%estimated ± 6.2 pp, medium confidence
GPQA Diamond68.8%estimated ± 2.4 pp, medium confidence
HLE16.7%estimated ± 8.5 pp, low confidence
IFBench54.9%estimated ± 6.6 pp, medium confidence
AA-LCR44.0%measured
AA-Omniscience Accuracy22.7%measured
SciCode44.2%estimated ± 3.6 pp, high confidence
BrowseComp67.7%estimated ± 6.2 pp, medium confidence
HLE w/ tools47.0%estimated ± 5.7 pp, medium confidence
IFEval90.3%estimated ± 2.8 pp, high confidence
LongBench v251.7%estimated ± 5.5 pp, medium confidence
τ²-bench results52.3%measured
AA Coding Index45.5%estimated ± 5.3 pp, medium confidence
AA-MMMU-Pro62.4%measured
APEX-Agents-AA21.9%estimated ± 3.6 pp, medium confidence
BioMysteryBench (human-difficult)18.0%estimated ± 6.8 pp, low confidence
DeepSearchQA76.0%estimated ± 8.2 pp, low confidence
SWE-bench Verified72.7%measured
BFCL v444.9%estimated ± 8.5 pp, low confidence
CyberGym51.4%estimated ± 11.0 pp, low confidence
JobBench18.4%measured
SWE-bench Pro50.4%estimated ± 4.5 pp, high confidence
WideResearch74.4%estimated ± 1.2 pp, medium confidence
AA Agentic Index16.7%estimated ± 9.4 pp, medium confidence
MMLU-Pro84.6%estimated ± 5.0 pp, medium confidence
AA-IFBench45.4%measured
AIME 202448.6%estimated ± 2.6 pp, high confidence
GPQA70.8%estimated ± 6.1 pp, medium confidence
MMLU90.3%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond67.4%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench73.8%estimated ± 10.0 pp, low confidence
Vals MMLU-Pro81.0%estimated ± 2.9 pp, high confidence
MATH-50091.4%estimated ± 2.0 pp, high confidence
MMMLU86.5%estimated ± 0.7 pp, medium confidence
MMMU74.8%estimated ± 2.7 pp, high confidence
AIME 202533.1%measured
AA MMLU-Pro84.5%estimated ± 0.8 pp, medium confidence
Gert Labs27.7%measured
AA EnterpriseOps-Gym41.3%estimated ± 1.2 pp, low confidence
ApprenticeBench0.2%estimated ± 6.0 pp, low confidence
ARC-AGI-175.6%estimated ± 7.8 pp, low confidence
ARC-AGI-232.7%estimated ± 14.4 pp, low confidence
FrontierCode 1.1 Main14.6%estimated ± 4.2 pp, low confidence
MazeBench0.0%estimated ± 2.7 pp, high confidence
OSWorld-Verified61.0%estimated ± 8.4 pp, low confidence
ParseBench-147.7%estimated ± 6.2 pp, medium confidence
Vals SWE-bench66.3%estimated ± 6.6 pp, medium confidence
CWE-Bench-AA38.3%estimated ± 8.1 pp, medium confidence
AA Cyber Index15.6%estimated ± 12.4 pp, low confidence
DeepsecBench-AA8.4%estimated ± 8.2 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)50.9%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)51.9%estimated ± 1.1 pp, low confidence
AA ITBench36.4%estimated ± 4.6 pp, medium confidence
CWE-bench v137.9%estimated ± 5.7 pp, medium confidence
DeepSWE34.1%estimated ± 12.7 pp, low confidence
HLE w/o tools29.1%estimated ± 4.9 pp, high confidence
OSWorld 2.17.7%estimated ± 3.6 pp, medium confidence
Toolathlon-Verified61.7%estimated ± 3.0 pp, high confidence
AA AutomationBench42.0%estimated ± 9.9 pp, low confidence
GDP.pdf16.4%estimated ± 4.1 pp, low confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
CWE-bench31.6%estimated ± 6.2 pp, low confidence
MKA32.8%estimated ± 4.6 pp, medium confidence
Vibe Code Bench0.4%estimated ± 8.4 pp, medium confidence
Hermes Index19.1%estimated ± 5.7 pp, low confidence
ParseBench-248.8%estimated ± 6.2 pp, medium confidence
CharXiv72.2%estimated ± 6.3 pp, low confidence
CharXiv w/o tools71.5%estimated ± 2.5 pp, medium confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
AI2D_TEST88.0%estimated ± 2.0 pp, medium confidence
C-Eval90.5%estimated ± 1.0 pp, medium confidence
Claw-Eval55.3%estimated ± 4.5 pp, medium confidence
CountBench85.8%estimated ± 2.9 pp, low confidence
DynaMath0.4%estimated ± 3.0 pp, low confidence
ERQA41.2%estimated ± 3.1 pp, medium confidence
HMMT Feb 202625.6%estimated ± 11.0 pp, low confidence
MathVision62.2%estimated ± 3.1 pp, medium confidence
MCP Atlas42.2%estimated ± 8.6 pp, medium confidence
MMLU-Redux93.8%estimated ± 0.8 pp, medium confidence
MMMU-Pro63.7%estimated ± 1.5 pp, high confidence
NL2Repo31.0%estimated ± 6.2 pp, medium confidence
PostTrainBench v112.0%estimated ± 5.5 pp, low confidence
RealWorldQA74.2%estimated ± 2.9 pp, low confidence
ScreenSpot Pro66.1%estimated ± 10.8 pp, low confidence
SuperGPQA65.1%estimated ± 9.3 pp, medium confidence
Toolathlon30.9%estimated ± 7.4 pp, low confidence
V*0.0%estimated ± 7.5 pp, low confidence
Video-MME (w/o subtitle)75.6%estimated ± 1.7 pp, medium confidence
Video-MME (with subtitle)76.2%estimated ± 3.7 pp, low confidence
HealthBench Hard10.4%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)7.6%estimated ± 6.5 pp, low confidence
MMLU-Pro (Arcee)81.3%estimated ± 4.0 pp, medium confidence
React Native Evals76.4%estimated ± 2.7 pp, medium confidence
ResearchClawBench15.2%estimated ± 2.6 pp, low confidence
SWE-Rebench57.0%estimated ± 3.6 pp, medium confidence
Finance Agent v255.1%estimated ± 2.4 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (length-adjusted)54.1%estimated ± 3.7 pp, medium confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HLE-Verified17.8%estimated ± 7.1 pp, low confidence
STEMBench2.4%estimated ± 0.2 pp, low confidence
SimpleQA21.8%estimated ± 4.3 pp, medium confidence
LiveCodeBench74.7%estimated ± 14.6 pp, low confidence
Agents' Last Exam29.6%estimated ± 9.7 pp, low confidence
MRCRv222.8%estimated ± 11.3 pp, low confidence
MMLongBench-Doc58.7%estimated ± 2.6 pp, low confidence
BioBasicsBench34.1%estimated ± 3.8 pp, low confidence
LifeVal4.5%estimated ± 5.0 pp, low confidence
MMMU-Pro w/ Python66.9%estimated ± 2.0 pp, medium confidence