Benchmarks

Table may be scrolled horizontally on narrow displays.

BenchmarkVersionOrganizationStatusRecords
AA-LCRUnknownArtificial AnalysisACTIVE371
AA-OmniscienceUnknownArtificial AnalysisACTIVE702
AIMEUnknownMAA (Mathematical Association of America)ACTIVE3
AIRS-BenchUnknownMeta FAIRACTIVE2
ApexUnknownMercorACTIVE2
Apex ShortlistUnknownUnknownACTIVE2
APEX-AgentsUnknownMercorACTIVE20
ARC-AGIUnknownARC Prize FoundationACTIVE1
Artificial Analysis Intelligence IndexUnknownArtificial AnalysisACTIVE398
Automation BenchUnknownZapierACTIVE2
BFCL-V4v4UC BerkeleyACTIVE1
BrowseCompUnknownOpenAIACTIVE9
BrowseComp-zhUnknownUnknownACTIVE1
C-EvalUnknownUnknownACTIVE1
ChartQAProUnknownYork UniversityACTIVE2
Chinese-SimpleQAUnknownAlibabaACTIVE2
Claw-EvalUnknownUnknownACTIVE1
CodeforcesUnknownCodeforcesACTIVE2
CorpusQAUnknownAlibabaACTIVE2
CritPtUnknownUnknownACTIVE355
CursorBenchUnknownCursor (Anysphere)ACTIVE1
DeepPlanningUnknownAlibaba (Qwen Team)ACTIVE1
DeepSWEUnknownDatacurveACTIVE15
Finance AgentUnknownVals AIACTIVE2
FrontierSWEUnknownProximal AIACTIVE1
GDPval-AAv2Artificial AnalysisACTIVE129
GPQAUnknownNew York UniversityACTIVE406
GraphWalksUnknownOpenAIACTIVE4
HLE-VerifiedUnknownAlibaba (Qwen Team)ACTIVE1
HMMTUnknownHarvard-MIT Mathematics TournamentACTIVE8
Humanity's Last ExamUnknownCenter for AI SafetyACTIVE411
IFBenchUnknownAllen Institute for AIACTIVE358
IFEvalUnknownGoogleACTIVE1
IMOAnswerBenchUnknownGoogle DeepMindACTIVE5
ITBench SREUnknownIBMACTIVE23
LiveCodeBenchUnknownUC BerkeleyACTIVE2
LiveCodeBench ProUnknownUnknownACTIVE1
LiveCodeBench v6v6UC BerkeleyACTIVE1
LongBench v2v2Tsinghua UniversityACTIVE1
MCP AtlasUnknownScale AIACTIVE7
MCP-MarkUnknownUnknownACTIVE1
MMLU-ProUnknownUniversity of Waterloo (TIGER-Lab)ACTIVE2
MMMLUUnknownOpenAIACTIVE3
MMMU-ProUnknownUnknownACTIVE153
MRCRUnknownGoogle DeepMindACTIVE2
MRCR v2v2Google DeepMindACTIVE2
MultiChallengeUnknownScale AIACTIVE1
NL2RepoUnknownUnknownACTIVE2
OSWorld-VerifiedUnknownXLang Lab (University of Hong Kong)ACTIVE2
PostTrainBenchUnknownThoughtfulACTIVE1
ProgramBenchUnknownMeta FAIRACTIVE1
SciCodeUnknownUniversity of Illinois Urbana-ChampaignACTIVE402
ScreenSpot-ProUnknownNational University of SingaporeACTIVE2
Seal-0UnknownVirginia TechACTIVE1
SecCodeBenchUnknownAlibabaACTIVE1
SimpleQA-VerifiedUnknownGoogle DeepMindACTIVE2
SkillsBenchUnknownBenchFlow AIACTIVE1
SuperGPQAUnknownByteDanceACTIVE1
SWE-benchUnknownPrinceton UniversityACTIVE25
SWE-MarathonUnknownAbundant AIACTIVE1
tau2-benchUnknownSierraACTIVE353
tau3-BankingUnknownArtificial AnalysisACTIVE119
Terminal-BenchUnknownLaude InstituteACTIVE121
Terminal-Bench HardUnknownLaude InstituteACTIVE345
Tool DecathlonUnknownHKUSTACTIVE2
ToolathlonUnknownHKUSTACTIVE2
Video-MMEUnknownTencentACTIVE1
VITA-BenchUnknownMeituanACTIVE1
WideSearchUnknownByteDanceACTIVE1