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.

40 models match “OpenAI”. Clear search

ModelPublished measuresContributing familiesWith independent supportExplore
GPT-5.6 Sol169266Published results
GPT-5.5113233Published results
GPT-5.6 Terra61184Published results
GPT-5.6 Luna53154Published results
GPT-6 Astra85134Published results
GPT-518111Published results
GPT-5 Mini19111Published results
GPT-5.117102Published results
GPT-5.43575Published results
GPT-6 Sol2472Published results
GPT-6.1 Sol1572Published results
GPT-4o Mini444Published results
o3444Published results
GPT-4.1333Published results
GPT-5.2433Published results
gpt-oss-120b433Published results
o3-mini333Published results
o4-mini333Published results
GPT-4-turbo222Published results
GPT-4.1 Mini222Published results
GPT-4o222Published results
GPT-6 Luna2022Published results
GPT-3.5-turbo-1106111Published results
GPT-4111Published results
GPT-4.1-nano111Published 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 1–25 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
GPT-5.6 Sol33.3
Provider reports · 9/9 reference peers
Unknown66.7
Provider reports · 8/8 reference peers
60.0
Provider reports · 12/12 reference peers
50.0
Provider reports · 5/5 reference peers
57.1
Provider reports · 16/16 reference peers
100.0
Provider reports · 2/2 reference peers
47.9
Independent support · 54/54 reference peers
Unknown33.3
Provider reports · 3/3 reference peers
40.0
Provider reports · 5/5 reference peers
100.0
Provider reports · 10/10 reference peers
25.0
Provider reports · 4/4 reference peers
85.6
Provider reports · 14/14 reference peers
85.0
Independent support · 20/20 reference peers
65.0
Independent support · 59/59 reference peers
Unknown68.3
Provider reports · 9/9 reference peers
UnknownUnknown33.3
Provider reports · 10/10 reference peers
Unknown79.2
Independent support · 30/30 reference peers
Unknown52.4
Independent support · 21/21 reference peers
Unknown100.0
Independent support · 41/41 reference peers
UnknownUnknownUnknownUnknownUnknown93.8
Provider reports · 7/7 reference peers
48.8
Provider reports · 9/9 reference peers
UnknownUnknown33.3
Provider reports · 3/3 reference peers
0.0
Provider reports · 1/1 reference peers
Unknown47.2
Provider reports · 8/8 reference peers
66.7
Provider reports · 3/3 reference peers
Unknown100.0
Provider reports · 4/4 reference peers
Unknown
GPT-5.537.4
Provider reports · 12/12 reference peers
0.0
Provider reports · 3/3 reference peers
62.9
Provider reports · 11/11 reference peers
34.4
Provider reports · 9/9 reference peers
35.2
Provider reports · 13/13 reference peers
10.0
Provider reports · 8/8 reference peers
100.0
Provider reports · 3/3 reference peers
65.1
Provider reports · 14/14 reference peers
Unknown100.0
Provider reports · 5/5 reference peers
60.0
Provider reports · 8/8 reference peers
66.7
Provider reports · 6/6 reference peers
Unknown8.3
Provider reports · 6/6 reference peers
68.3
Provider reports · 8/8 reference peers
66.5
Independent support · 59/59 reference peers
Unknown63.3
Provider reports · 6/6 reference peers
Unknown83.3
Provider reports · 6/6 reference peers
36.1
Provider reports · 12/12 reference peers
Unknown59.1
Independent support · 27/27 reference peers
UnknownUnknownUnknown89.5
Independent support · 76/76 reference peers
UnknownUnknownUnknownUnknownUnknown67.4
Provider reports · 11/11 reference peers
22.9
Provider reports · 6/6 reference peers
UnknownUnknownUnknownUnknownUnknown83.3
Provider reports · 5/5 reference peers
UnknownUnknown0.0
Provider reports · 4/4 reference peers
Unknown
GPT-5.6 Terra50.0
Provider reports · 4/4 reference peers
Unknown80.0
Provider reports · 5/5 reference peers
16.7
Provider reports · 6/6 reference peers
Unknown50.0
Provider reports · 6/6 reference peers
Unknown38.6
Provider reports · 11/11 reference peers
UnknownUnknownUnknown35.0
Provider reports · 10/10 reference peers
Unknown20.0
Provider reports · 5/5 reference peers
50.0
Independent support · 8/8 reference peers
76.1
Independent support · 59/59 reference peers
Unknown45.0
Provider reports · 6/6 reference peers
UnknownUnknown50.0
Provider reports · 6/6 reference peers
Unknown66.0
Independent support · 27/27 reference peers
Unknown49.0
Independent support · 21/21 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknown41.7
Provider reports · 4/4 reference peers
80.0
Provider reports · 5/5 reference peers
UnknownUnknown0.0
Provider reports · 3/3 reference peers
UnknownUnknown50.0
Provider reports · 3/3 reference peers
UnknownUnknown50.0
Provider reports · 4/4 reference peers
Unknown
GPT-5.6 Luna0.0
Provider reports · 4/4 reference peers
Unknown0.0
Provider reports · 5/5 reference peers
33.3
Provider reports · 6/6 reference peers
Unknown33.3
Provider reports · 6/6 reference peers
Unknown42.9
Provider reports · 7/7 reference peers
UnknownUnknownUnknown33.3
Provider reports · 6/6 reference peers
UnknownUnknown8.3
Independent support · 7/7 reference peers
25.4
Independent support · 59/59 reference peers
Unknown18.3
Provider reports · 6/6 reference peers
UnknownUnknown33.3
Provider reports · 6/6 reference peers
Unknown58.3
Independent support · 27/27 reference peers
Unknown23.8
Independent support · 21/21 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknown0.0
Provider reports · 4/4 reference peers
UnknownUnknownUnknownUnknownUnknownUnknown0.0
Provider reports · 3/3 reference peers
UnknownUnknown37.5
Provider reports · 4/4 reference peers
Unknown
GPT-6 Astra100.0
Provider reports · 4/4 reference peers
Unknown100.0
Provider reports · 3/3 reference peers
UnknownUnknown100.0
Provider reports · 6/6 reference peers
UnknownUnknownUnknownUnknownUnknown85.0
Provider reports · 2/2 reference peers
100.0
Provider reports · 6/6 reference peers
0.0
Provider reports · 3/3 reference peers
100.0
Independent support · 12/12 reference peers
96.9
Independent support · 59/59 reference peers
Unknown100.0
Provider reports · 4/4 reference peers
UnknownUnknownUnknownUnknown91.7
Independent support · 30/30 reference peers
Unknown96.4
Independent support · 21/21 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown100.0
Provider reports · 1/1 reference peers
Unknown100.0
Provider reports · 1/1 reference peers
UnknownUnknownUnknownUnknown
GPT-5UnknownUnknownUnknownUnknown100.0
Provider reports · 4/4 reference peers
UnknownUnknownUnknown77.3
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknownUnknown81.8
Provider reports · 11/11 reference peers
33.9
Independent support · 59/59 reference peers
100.0
Provider reports · 11/11 reference peers
UnknownUnknown66.7
Provider reports · 9/9 reference peers
UnknownUnknownUnknown88.9
Provider reports · 9/9 reference peers
UnknownUnknownUnknown90.9
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknown100.0
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknown33.3
Provider reports · 9/9 reference peers
54.5
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknownUnknown
GPT-5 MiniUnknownUnknownUnknownUnknown25.0
Provider reports · 4/4 reference peers
UnknownUnknownUnknown45.5
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknownUnknown54.5
Provider reports · 11/11 reference peers
22.0
Independent support · 59/59 reference peers
72.7
Provider reports · 11/11 reference peers
UnknownUnknown55.6
Provider reports · 9/9 reference peers
UnknownUnknownUnknown77.8
Provider reports · 9/9 reference peers
UnknownUnknownUnknown63.6
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknown81.8
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknown0.0
Provider reports · 9/9 reference peers
27.3
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknownUnknown
GPT-5.1UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown54.5
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknownUnknown100.0
Provider reports · 11/11 reference peers
Unknown90.9
Provider reports · 11/11 reference peers
UnknownUnknown88.9
Provider reports · 9/9 reference peers
UnknownUnknownUnknown100.0
Provider reports · 9/9 reference peers
UnknownUnknown63.2
Independent support · 76/76 reference peers
85.0
Independent support · 61/61 reference peers
UnknownUnknownUnknownUnknown90.9
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknown22.2
Provider reports · 9/9 reference peers
45.5
Provider reports · 11/11 reference peers
UnknownUnknownUnknownUnknownUnknown
GPT-5.4UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown100.0
Provider reports · 5/5 reference peers
71.2
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknown58.3
Independent support · 6/6 reference peers
Unknown22.2
Independent support · 27/27 reference peers
UnknownUnknownUnknown81.6
Independent support · 76/76 reference peers
94.1
Independent support · 51/51 reference peers
UnknownUnknownUnknownUnknownUnknown100.0
Provider reports · 2/2 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
GPT-6 Sol0.0
Provider reports · 2/2 reference peers
UnknownUnknownUnknownUnknown0.0
Provider reports · 2/2 reference peers
UnknownUnknownUnknownUnknownUnknown0.0
Provider reports · 2/2 reference peers
0.0
Provider reports · 2/2 reference peers
UnknownUnknown88.1
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknown0.0
Provider reports · 2/2 reference peers
Unknown76.2
Independent support · 21/21 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
GPT-6.1 Sol50.0
Provider reports · 2/2 reference peers
UnknownUnknownUnknownUnknown50.0
Provider reports · 2/2 reference peers
UnknownUnknownUnknownUnknownUnknown65.0
Provider reports · 2/2 reference peers
50.0
Provider reports · 2/2 reference peers
UnknownUnknown98.3
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknown70.0
Provider reports · 2/2 reference peers
Unknown92.9
Independent support · 21/21 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
GPT-4o MiniUnknownUnknownUnknownUnknownUnknownUnknownUnknown4.8
Independent support · 42/42 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknown3.4
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknown0.0
Independent support · 8/8 reference peers
UnknownUnknownUnknown33.3
Independent support · 51/51 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
o30.0
Independent support · 5/5 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown32.2
Independent support · 59/59 reference peers
UnknownUnknownUnknown50.0
Independent support · 18/18 reference peers
UnknownUnknownUnknown87.5
Independent support · 8/8 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
GPT-4.1UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown12.5
Independent support · 8/8 reference peers
Unknown8.5
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown64.7
Independent support · 51/51 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
GPT-5.2UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown45.8
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown59.2
Independent support · 76/76 reference peers
92.2
Independent support · 51/51 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
gpt-oss-120bUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown0.0
Independent support · 2/2 reference peers
UnknownUnknownUnknownUnknown5.6
Independent support · 18/18 reference peers
UnknownUnknownUnknownUnknownUnknownUnknown21.1
Independent support · 76/76 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
o3-miniUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown16.9
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknown50.0
Independent support · 8/8 reference peers
UnknownUnknown19.7
Independent support · 76/76 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
o4-miniUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown30.5
Independent support · 59/59 reference peers
UnknownUnknownUnknown16.7
Independent support · 18/18 reference peers
UnknownUnknownUnknown100.0
Independent support · 8/8 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
GPT-4-turboUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown12.5
Independent support · 8/8 reference peers
UnknownUnknownUnknown35.3
Independent support · 51/51 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
GPT-4.1 MiniUnknownUnknownUnknownUnknownUnknownUnknownUnknown23.8
Independent support · 42/42 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknown3.4
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
GPT-4oUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown3.4
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknown25.0
Independent support · 8/8 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
GPT-6 LunaUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown49.2
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown19.0
Independent support · 21/21 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
GPT-3.5-turbo-1106UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown22.0
Independent support · 41/41 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
GPT-4UnknownUnknownUnknownUnknownUnknownUnknownUnknown7.1
Independent support · 42/42 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown
GPT-4.1-nanoUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown3.4
Independent support · 59/59 reference peers
UnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknownUnknown

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