Evidence coverage

3498 published observations across 337 measures. Capability scoring groups compatible evidence into 44 benchmark families.

A published result contributes only when a matching reference-panel result is available. Missing evidence stays unknown. Coverage describes breadth, separately from performance.

Coverage across our labs

LabModels with resultsPublished measuresLaunch sources
OpenAI34 / 4024120
Anthropic14 / 1425122
xAI4 / 8352
Google22 / 351339
Meta14 / 16462
Mistral17 / 28392
Moonshot3 / 71337
Qwen32 / 821044
DeepSeek7 / 16332
NVIDIA2 / 10471
Z.ai17 / 521057
MiniMax6 / 14692
Cohere10 / 26181
Amazon5 / 6201
Microsoft9 / 24191
Xiaomi5 / 14100
StepFun3 / 550
LG AI Research5 / 1330
Upstage5 / 940
ByteDance1 / 1610
Tencent2 / 1370
Baidu1 / 2010
OpenBMB1 / 120
Agnes AI1 / 220

Models and contributing families

Raw published counts include all source types. Contributing and independent family counts follow the selected evidence policy.

14 models match “Anthropic”. Clear search

ModelPublished measuresContributing familiesWith independent supportExplore
Claude Fable 5124244Published results
Claude Opus 4.8113234Published results
Claude Opus 578227Published results
Claude Fable 5.166163Published results
Claude Sonnet 4.641164Published results
Claude Sonnet 4.530145Published results
Claude Opus 4.734112Published results
Claude Haiku 4.518103Published results
Claude Sonnet 52172Published results
Claude Opus 4.63553Published results
Claude Opus 4.5333Published results
Claude Haiku 5.53522Published results
Claude Sonnet 5.5822Published results
Claude Opus 5.54811Published results

Family coverage

Benchmark familyCapabilityModels contributingWith independent support
OSWorldAgentic216
Webarena VerifiedAgentic40
BrowsecompAgentic220
ToolathlonAgentic150
MCP-AtlasAgentic190
AutomationBenchAgentic210
DeepSearchQAAgentic100
GDPvalAgentic6445
Bfcl V4Agentic120
Apex AgentsAgentic100
OfficeQAAgentic110
GDP.pdfAgentic140
Terminal-Bench ScienceAgentic70
Humanity’s Last ExamHard reasoning329
GPQAHard reasoning4518
ARC-AGIHard reasoning6060
AimeHard reasoning220
FrontierMathHard reasoning100
Imo AnswerbenchHard reasoning50
SWE-bench VerifiedCoding3819
SWE-bench ProCoding204
SWE-bench MultilingualCoding90
DeepSWECoding3328
LiveCodeBenchCoding259
Terminal-BenchCoding2222
ScicodeCoding00
Human preference (Arena)Human pref119119
MMLU-ProKnowledge6852
GmmluKnowledge30
MiluKnowledge30
Simpleqa VerifiedKnowledge20
MmmuMultimodal20
Mmmu ProMultimodal240
CharXivMultimodal160
MathvistaMultimodal20
ChartographyMultimodal30
LvbenchMultimodal60
ScreenSpotMultimodal120
Ocrbench V2 Average AccuracyMultimodal120
MRCRLong context120
LongbenchLong context80
Ruler 1MLong context20
GraphwalksLong context70
Aa LcrLong context50
Model evidence matrix

Showing the same 1–14 models as the list above.

ModelOSWorldWebarena VerifiedBrowsecompToolathlonMCP-AtlasAutomationBenchDeepSearchQAGDPvalBfcl V4Apex AgentsOfficeQAGDP.pdfTerminal-Bench ScienceHumanity’s Last ExamGPQAARC-AGIAimeFrontierMathImo AnswerbenchSWE-bench VerifiedSWE-bench ProSWE-bench MultilingualDeepSWELiveCodeBenchTerminal-BenchScicodeHuman preference (Arena)MMLU-ProGmmluMiluSimpleqa VerifiedMmmuMmmu ProCharXivMathvistaChartographyLvbenchScreenSpotOcrbench V2 Average AccuracyMRCRLongbenchRuler 1MGraphwalksAa Lcr
Claude Fable 566.7
Independent support · 10/10 reference peers
Unknown0.0
Provider reports · 3/3 reference peers
100.0
Provider reports · 8/8 reference peers
100.0
Provider reports · 5/5 reference peers
33.9
Provider reports · 11/11 reference peers
50.0
Provider reports · 2/2 reference peers
66.7
Provider reports · 11/11 reference peers
Unknown100.0
Provider reports · 3/3 reference peers
100.0
Provider reports · 5/5 reference peers
83.3
Provider reports · 6/6 reference peers
0.0
Provider reports · 4/4 reference peers
72.2
Provider reports · 7/7 reference peers
28.3
Provider reports · 12/12 reference peers
59.8
Independent support · 59/59 reference peers
Unknown86.1
Provider reports · 9/9 reference peers
UnknownUnknown83.3
Provider reports · 8/8 reference peers
0.0
Provider reports · 2/2 reference peers
70.9
Independent support · 28/28 reference peers
Unknown37.1
Independent support · 21/21 reference peers
UnknownUnknownUnknown50.0
Provider reports · 2/2 reference peers
50.0
Provider reports · 2/2 reference peers
UnknownUnknown68.8
Provider reports · 4/4 reference peers
100.0
Provider reports · 4/4 reference peers
Unknown50.0
Provider reports · 2/2 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
Claude Opus 4.870.8
Provider reports · 8/8 reference peers
100.0
Provider reports · 3/3 reference peers
20.0
Provider reports · 5/5 reference peers
83.6
Provider reports · 14/14 reference peers
58.3
Provider reports · 7/7 reference peers
44.7
Provider reports · 13/13 reference peers
16.7
Provider reports · 5/5 reference peers
85.7
Provider reports · 8/8 reference peers
UnknownUnknown80.0
Provider reports · 5/5 reference peers
16.7
Provider reports · 6/6 reference peers
Unknown63.3
Provider reports · 12/12 reference peers
0.0
Provider reports · 10/10 reference peers
66.9
Independent support · 59/59 reference peers
Unknown16.7
Provider reports · 6/6 reference peers
UnknownUnknown94.4
Provider reports · 9/9 reference peers
Unknown43.1
Independent support · 28/28 reference peers
Unknown42.9
Independent support · 21/21 reference peers
Unknown86.8
Independent support · 76/76 reference peers
UnknownUnknownUnknownUnknownUnknown0.0
Provider reports · 4/4 reference peers
62.5
Provider reports · 6/6 reference peers
UnknownUnknownUnknownUnknownUnknown0.0
Provider reports · 3/3 reference peers
100.0
Provider reports · 3/3 reference peers
Unknown62.5
Provider reports · 4/4 reference peers
Unknown
Claude Opus 563.7
Independent support · 9/9 reference peers
Unknown66.7
Provider reports · 3/3 reference peers
UnknownUnknown72.2
Provider reports · 5/5 reference peers
50.0
Provider reports · 2/2 reference peers
91.7
Independent support · 49/49 reference peers
UnknownUnknown0.0
Provider reports · 1/1 reference peers
80.0
Provider reports · 5/5 reference peers
50.0
Provider reports · 4/4 reference peers
31.1
Provider reports · 8/8 reference peers
65.0
Independent support · 6/6 reference peers
69.4
Independent support · 59/59 reference peers
Unknown0.0
Provider reports · 4/4 reference peers
UnknownUnknown33.3
Provider reports · 3/3 reference peers
100.0
Provider reports · 2/2 reference peers
76.3
Independent support · 28/28 reference peers
Unknown72.7
Independent support · 21/21 reference peers
Unknown97.4
Independent support · 76/76 reference peers
Unknown0.0
Provider reports · 2/2 reference peers
0.0
Provider reports · 2/2 reference peers
UnknownUnknownUnknown20.0
Provider reports · 5/5 reference peers
Unknown0.0
Provider reports · 2/2 reference peers
100.0
Provider reports · 1/1 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknown
Claude Fable 5.1100.0
Provider reports · 2/2 reference peers
UnknownUnknownUnknownUnknown87.5
Provider reports · 4/4 reference peers
Unknown100.0
Provider reports · 3/3 reference peers
UnknownUnknown100.0
Provider reports · 1/1 reference peers
Unknown75.0
Provider reports · 4/4 reference peers
100.0
Provider reports · 3/3 reference peers
40.0
Independent support · 12/12 reference peers
52.2
Independent support · 59/59 reference peers
Unknown50.0
Provider reports · 4/4 reference peers
UnknownUnknown100.0
Provider reports · 3/3 reference peers
50.0
Provider reports · 2/2 reference peers
0.0
Provider reports · 5/5 reference peers
Unknown88.6
Independent support · 21/21 reference peers
UnknownUnknownUnknown100.0
Provider reports · 2/2 reference peers
100.0
Provider reports · 2/2 reference peers
UnknownUnknownUnknownUnknownUnknown100.0
Provider reports · 2/2 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
Claude Sonnet 4.620.0
Independent support · 10/10 reference peers
Unknown25.0
Provider reports · 10/10 reference peers
Unknown14.3
Provider reports · 7/7 reference peers
UnknownUnknown71.4
Provider reports · 7/7 reference peers
Unknown20.0
Provider reports · 5/5 reference peers
UnknownUnknownUnknownUnknown40.0
Provider reports · 5/5 reference peers
54.2
Independent support · 59/59 reference peers
37.5
Provider reports · 6/6 reference peers
UnknownUnknown36.1
Provider reports · 12/12 reference peers
UnknownUnknown3.7
Independent support · 27/27 reference peers
UnknownUnknownUnknown85.5
Independent support · 76/76 reference peers
100.0
Provider reports · 1/1 reference peers
UnknownUnknown0.0
Provider reports · 1/1 reference peers
Unknown0.0
Provider reports · 5/5 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknown100.0
Provider reports · 1/1 reference peers
Unknown100.0
Provider reports · 1/1 reference peers
Unknown
Claude Sonnet 4.520.0
Independent support · 5/5 reference peers
Unknown0.0
Provider reports · 4/4 reference peers
Unknown75.0
Provider reports · 4/4 reference peers
UnknownUnknownUnknown100.0
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknown37.5
Independent support · 8/8 reference peers
72.7
Provider reports · 11/11 reference peers
18.6
Independent support · 59/59 reference peers
47.7
Provider reports · 15/15 reference peers
UnknownUnknown65.7
Independent support · 28/28 reference peers
UnknownUnknownUnknown44.4
Provider reports · 9/9 reference peers
UnknownUnknown87.8
Independent support · 41/41 reference peers
100.0
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknown68.2
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknownUnknown9.1
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknownUnknown
Claude Opus 4.7100.0
Provider reports · 5/5 reference peers
Unknown35.7
Provider reports · 7/7 reference peers
Unknown100.0
Provider reports · 7/7 reference peers
UnknownUnknown85.7
Provider reports · 7/7 reference peers
Unknown80.0
Provider reports · 5/5 reference peers
33.3
Provider reports · 3/3 reference peers
UnknownUnknown75.0
Independent support · 8/8 reference peers
UnknownUnknownUnknownUnknownUnknown100.0
Provider reports · 6/6 reference peers
100.0
Provider reports · 6/6 reference peers
UnknownUnknownUnknownUnknownUnknown98.7
Independent support · 76/76 reference peers
UnknownUnknownUnknownUnknownUnknown20.0
Provider reports · 5/5 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
Claude Haiku 4.5UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown90.9
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknownUnknown27.3
Provider reports · 11/11 reference peers
11.0
Independent support · 59/59 reference peers
36.4
Provider reports · 11/11 reference peers
UnknownUnknown69.4
Independent support · 24/24 reference peers
UnknownUnknownUnknown11.1
Provider reports · 9/9 reference peers
UnknownUnknown75.6
Independent support · 41/41 reference peers
27.3
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknown27.3
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknownUnknown0.0
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknownUnknown
Claude Sonnet 5UnknownUnknownUnknownUnknownUnknownUnknownUnknown60.0
Provider reports · 5/5 reference peers
UnknownUnknownUnknown0.0
Provider reports · 5/5 reference peers
Unknown0.0
Provider reports · 5/5 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown17.6
Independent support · 27/27 reference peers
Unknown13.6
Independent support · 21/21 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown0.0
Provider reports · 5/5 reference peers
UnknownUnknown0.0
Provider reports · 1/1 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknown
Claude Opus 4.6UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown80.0
Provider reports · 5/5 reference peers
Unknown100.0
Provider reports · 2/2 reference peers
UnknownUnknown94.4
Independent support · 21/21 reference peers
29.2
Independent support · 6/6 reference peers
UnknownUnknownUnknownUnknownUnknown100.0
Independent support · 76/76 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
Claude Opus 4.5UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown50.0
Independent support · 8/8 reference peers
UnknownUnknownUnknownUnknownUnknown83.3
Independent support · 18/18 reference peers
UnknownUnknownUnknownUnknownUnknownUnknown97.6
Independent support · 41/41 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
Claude Haiku 5.5UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown62.5
Independent support · 8/8 reference peers
Unknown58.5
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
Claude Sonnet 5.5UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown77.1
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown100.0
Independent support · 21/21 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
Claude Opus 5.5UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown96.6
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown

Family definitions and scoring rules · Compare capabilities · Compare published evidence