benchgap
Anthropic · model

Claude Opus 4.7 benchmark scores

As of 2026-11-22, Claude Opus 4.7 (Anthropic) has measured scores on 55 benchmarks and estimated scores on 142 more.

BenchmarkScoreSource
AA-GPQA Diamond91.4%measured
AA-HLE42.3%measured
AA-SciCode55.5%estimated ± 3.4 pp, high confidence
AIME2699.2%estimated ± 1.2 pp, low confidence
Artificial Analysis Intelligence Index40.7%measured
CritPt12.0%measured
GDPval-AA42.6%measured
GPQA Diamond94.2%measured
HLE54.7%measured
IFBench59.3%estimated ± 6.6 pp, medium confidence
AA-LCR78.7%measured
LiveCodeBench v688.8%estimated ± 2.2 pp, medium confidence
AA-Omniscience Accuracy48.9%measured
SciCode46.9%estimated ± 2.9 pp, medium confidence
Terminal-Bench 2.183.7%estimated ± 6.7 pp, medium confidence
BrowseComp79.3%measured
HLE w/ tools50.1%estimated ± 4.9 pp, medium confidence
IFEval92.1%estimated ± 2.8 pp, high confidence
LongBench v264.6%estimated ± 5.5 pp, medium confidence
VITA-Bench44.6%estimated ± 6.7 pp, low confidence
τ²-bench results88.6%measured
AA Coding Index73.6%measured
AA-MMMU-Pro78.8%measured
APEX-Agents34.6%estimated ± 9.4 pp, low confidence
APEX-Agents-AA36.1%estimated ± 2.9 pp, medium confidence
BioMysteryBench (human-difficult)45.1%estimated ± 6.8 pp, low confidence
DeepSearchQA91.6%estimated ± 4.5 pp, high confidence
SWE-bench Verified87.6%measured
AutomationBench29.2%estimated ± 10.4 pp, low confidence
BFCL v476.0%estimated ± 2.7 pp, medium confidence
CyberGym73.1%measured
JobBench45.9%measured
SkillsBench50.6%estimated ± 4.1 pp, medium confidence
SWE-bench Pro64.3%measured
WideResearch80.4%estimated ± 1.2 pp, medium confidence
AA Agentic Index39.5%measured
MMLU-Pro85.8%estimated ± 2.5 pp, low confidence
AA-IFBench58.6%measured
FailureSensorIQ66.5%estimated ± 2.1 pp, high confidence
GPQA94.2%measured
MMLU90.5%estimated ± 0.9 pp, medium confidence
Vals GPQA Diamond90.2%measured
Vals LiveCodeBench85.1%measured
Vals MMLU-Pro89.9%measured
MMMLU89.8%estimated ± 0.7 pp, medium confidence
MMMU85.7%estimated ± 2.7 pp, high confidence
Chess Puzzles41.0%measured
AA MMLU-Pro88.7%estimated ± 0.7 pp, high confidence
Gert Labs47.8%measured
AA-AnalystAgent46.5%estimated ± 3.7 pp, medium confidence
AA EnterpriseOps-Gym45.8%estimated ± 1.2 pp, medium confidence
AA Harvey LAB v1.092.1%estimated ± 1.2 pp, medium confidence
AA Tau3 Banking39.4%estimated ± 3.3 pp, low confidence
AA Terminal-Bench 2.183.1%measured
ApprenticeBench7.0%measured
ARC-AGI-193.8%estimated ± 1.7 pp, high confidence
ARC-AGI-275.8%measured
BabaIsBench94.5%estimated ± 1.2 pp, high confidence
CursorBench 3.155.2%estimated ± 4.8 pp, medium confidence
CursorBench 3.255.6%estimated ± 1.6 pp, low confidence
EBR-bench19.0%measured
Terminal-Bench 3.011.9%estimated ± 6.9 pp, medium confidence
FrontierCode 1.1 Main38.5%measured
FrontierMath v2 (Tier 4)31.7%measured
FrontierMath v2 (Tiers 1-3)70.2%measured
FrontierSWE v223.0%estimated ± 8.3 pp, medium confidence
Furniture Assembly33.3%measured
MaxxBench48.4%estimated ± 4.3 pp, low confidence
MazeBench0.5%estimated ± 2.7 pp, high confidence
MirrorCode43.3%measured
Mystery Game Puzzles28.0%measured
NYT Connections83.0%estimated ± 12.6 pp, low confidence
OfficeQA Pro43.6%measured
OSWorld-Verified78.0%measured
ParseBench-163.3%measured
Terminal-Bench 4.117.4%estimated ± 14.9 pp, low confidence
Terminal-Bench Hard52.4%estimated ± 3.9 pp, high confidence
Vals SWE-bench82.0%measured
Terminal-Bench 2.1 (Vals AI)68.5%measured
VulcanBench v383.7%estimated ± 5.6 pp, low confidence
CWE-Bench-AA46.1%estimated ± 4.5 pp, medium confidence
AA Cyber Index24.2%estimated ± 9.2 pp, low confidence
DeepsecBench-AA16.3%estimated ± 8.2 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)58.2%estimated ± 4.3 pp, medium confidence
HealthBench Professional (raw, Artificial Analysis)58.2%estimated ± 0.8 pp, low confidence
AA ITBench46.7%measured
Bug Hunt Bench17.3%estimated ± 6.3 pp, low confidence
Chartography (tools)82.6%estimated ± 4.1 pp, low confidence
CursorBench 4.038.1%estimated ± 2.0 pp, high confidence
CWE-bench v149.3%estimated ± 5.7 pp, medium confidence
DeepSWE62.1%estimated ± 4.3 pp, high confidence
DRACO81.8%estimated ± 2.0 pp, medium confidence
FrontierCode 2.020.0%estimated ± 6.0 pp, medium confidence
FrontierPhysics1.2%estimated ± 4.4 pp, high confidence
HLE w/o tools46.9%measured
OSWorld 2.018.2%measured
OSWorld 2.158.7%estimated ± 3.6 pp, high confidence
OSWorld 2.1 Offline37.0%estimated ± 1.9 pp, low confidence
PostTrainBench v1.128.6%measured
ProgramBench0.5%estimated ± 4.8 pp, low confidence
SpireClimb0.1%estimated ± 9.3 pp, medium confidence
StealthMark45.6%estimated ± 6.5 pp, medium confidence
SWE-bench Multimodal45.2%estimated ± 5.6 pp, low confidence
Toolathlon-Verified72.3%estimated ± 1.0 pp, low confidence
VulcanBench Frontier v480.6%estimated ± 2.8 pp, medium confidence
AA AutomationBench53.0%estimated ± 9.9 pp, low confidence
GDP.pdf16.5%estimated ± 4.1 pp, medium confidence
AA Terminal-Bench 4.025.2%estimated ± 13.7 pp, low confidence
ARC-AGI-30.2%measured
ARC-AGI-3 Provider Adapter1.0%estimated ± 4.4 pp, high confidence
CWE-bench45.6%estimated ± 6.2 pp, medium confidence
MKA35.1%estimated ± 4.6 pp, high confidence
SkillsBench official leaderboard (BenchFlow)61.2%measured
BinaryAudit47.2%estimated ± 12.0 pp, low confidence
CompileBench100.0%estimated ± 10.0 pp, low confidence
OTelBench30.3%estimated ± 4.1 pp, low confidence
Vibe Code Bench71.0%measured
FACTS Multimodal43.9%estimated ± 5.6 pp, medium confidence
Hermes Bench67.2%estimated ± 2.9 pp, high confidence
Hermes Index31.2%estimated ± 5.7 pp, low confidence
ParseBench-269.0%estimated ± 3.5 pp, high confidence
CharXiv91.0%measured
CharXiv w/o tools82.1%measured
ExploitBench32.4%estimated ± 6.5 pp, low confidence
ExploitGym3.6%estimated ± 8.3 pp, low confidence
AI2D_TEST93.5%estimated ± 0.9 pp, low confidence
C-Eval97.7%estimated ± 1.0 pp, low confidence
Claw-Eval73.3%estimated ± 3.2 pp, medium confidence
CountBench97.4%estimated ± 2.9 pp, medium confidence
DeepPlanning48.8%estimated ± 13.1 pp, low confidence
DynaMath88.2%estimated ± 0.8 pp, low confidence
ERQA66.3%estimated ± 2.9 pp, medium confidence
HMMT Feb 202695.4%estimated ± 1.5 pp, medium confidence
HMMT Nov 202595.5%estimated ± 1.5 pp, low confidence
MathVision89.5%estimated ± 3.1 pp, high confidence
MCP Atlas77.3%measured
MLVU (M-Avg)89.3%estimated ± 1.5 pp, high confidence
MMAnswerBench91.7%estimated ± 2.4 pp, low confidence
MMLU-Redux97.1%estimated ± 0.8 pp, low confidence
MMMU-Pro79.6%estimated ± 1.5 pp, high confidence
NL2Repo46.9%estimated ± 4.7 pp, high confidence
PostTrainBench v128.6%measured
QwenClawBench63.9%estimated ± 2.6 pp, medium confidence
RealWorldQA87.7%estimated ± 1.5 pp, high confidence
ScreenSpot Pro86.1%estimated ± 6.8 pp, medium confidence
SuperGPQA93.7%estimated ± 7.2 pp, low confidence
Terminal-Bench 2.069.4%measured
Toolathlon53.0%estimated ± 1.7 pp, medium confidence
V*100.0%estimated ± 7.5 pp, medium confidence
Video-MME (w/o subtitle)85.8%estimated ± 1.7 pp, medium confidence
Video-MME (with subtitle)91.1%estimated ± 2.9 pp, high confidence
VideoMMMU87.5%estimated ± 1.5 pp, medium confidence
We-Math84.6%estimated ± 7.9 pp, low confidence
AA LiveCodeBench92.8%estimated ± 2.6 pp, medium confidence
HealthBench Hard36.5%estimated ± 5.1 pp, low confidence
LiveCodeBench Pro87.0%estimated ± 6.0 pp, low confidence
MedXpertQA (MM)79.4%estimated ± 6.4 pp, low confidence
MedXpertQA (Text)68.9%estimated ± 4.5 pp, medium confidence
MMLU-Pro (Arcee)88.2%estimated ± 3.4 pp, low confidence
React Native Evals82.8%measured
ResearchClawBench20.7%measured
SWE-Rebench61.8%estimated ± 3.6 pp, low confidence
PostTrainBench24.3%measured
DAYJOB1.4%estimated ± 2.7 pp, high confidence
DAYJOB Healthcare0.0%estimated ± 4.0 pp, high confidence
Finance Agent v255.6%estimated ± 2.4 pp, medium confidence
BioMysteryBench (human-solvable)85.1%estimated ± 0.6 pp, low confidence
FrontierCode 1.1 Extended57.4%estimated ± 3.0 pp, medium confidence
HealthBench (raw)50.8%estimated ± 6.0 pp, medium confidence
HealthBench (length-adjusted)53.8%estimated ± 0.9 pp, medium confidence
HealthBench Professional56.8%estimated ± 3.6 pp, high confidence
HealthBench Professional (raw)61.3%estimated ± 4.5 pp, high confidence
HLE-Verified48.2%estimated ± 1.3 pp, low confidence
LABBench283.0%estimated ± 1.8 pp, low confidence
ScarfBench57.2%estimated ± 5.5 pp, low confidence
BlenderWorld (text-only)70.6%estimated ± 2.8 pp, medium confidence
Cookie-Bench78.5%estimated ± 1.3 pp, medium confidence
STEMBench2.6%estimated ± 0.2 pp, medium confidence
SimpleQA34.3%estimated ± 7.8 pp, low confidence
LiveCodeBench83.7%estimated ± 14.6 pp, low confidence
Agents' Last Exam24.9%estimated ± 3.3 pp, low confidence
BabyVision w/ Python88.2%estimated ± 3.7 pp, low confidence
OpenHarmony Bench v1.058.1%estimated ± 2.8 pp, high confidence
SEC-Bench Pro36.9%estimated ± 7.5 pp, low confidence
BabyVision55.2%estimated ± 7.4 pp, low confidence
MMVU81.1%estimated ± 3.6 pp, medium confidence
PerceptionBench55.3%estimated ± 3.8 pp, medium confidence
ZeroBench20.4%estimated ± 7.1 pp, low confidence
MRCRv285.6%estimated ± 11.3 pp, low confidence
LVBench74.0%estimated ± 8.2 pp, low confidence
MMLongBench-Doc61.4%estimated ± 2.6 pp, low confidence
BioBasicsBench41.9%estimated ± 2.2 pp, medium confidence
LifeVal70.7%estimated ± 1.6 pp, medium confidence
MMMU-Pro w/ Python81.6%estimated ± 2.0 pp, high confidence
ExploitBench Internal Port0.5%estimated ± 1.4 pp, medium confidence
MathVision w/ Python96.3%estimated ± 1.0 pp, low confidence
PinchBench90.2%estimated ± 3.6 pp, medium confidence