Atlas Graph Explorer

Wiki Graph Edges

Clusters

catalog-meta1769

CiSurface1
Claim825
ClaimTest5
ClaimTestRun5
DeploymentTarget2
EvidencePolicy2
EvidenceSource227
Gap4
Grammar1
MetaAttribute366
MetaCluster16
MetaEdgeKind84
MetaEnum34
MetaNodeKind114
OntologySchema1
OpenQuestion5
OutOfScopeReason4
PackageSurface23
PathDescriptor45
RunJournalEvent5

extensions1288

domain1003

Domain108
Framework36
Language39
Library63
Platform10
PlatformService65
SkillArea319
Specialization39
StackPart52
StackProfile7
Tool101
Topic164

workflows668

Workflow668

terminology444

Acronym25
Definition116
Synonym11
Term292

agent-stack349

AgentCoreImpl28
AgentPlatformImpl20
AgentProduct38
AgentRuntimeImpl24
AgentUIImpl18
AgentVersion42
CapabilityProfile3
InteractionPrimitive257
InteractionPrimitiveCategory12
LaunchConfig10
Presentation22
SessionModel4

benchmarks232

Benchmark65
EvalHarness5
EvalResult73
EvalRun70
Judge3
Rubric3
TestSet13

role186

Customer3
EndUser3
OrgUnit59
Responsibility49
Role66
Tenant3
VendorRelationship3

sourceref-scope175

ScopeBoundary111
SourceRef64

channels-hooks137

Channel6
DecisionVerb5
HookMapping54
HookSurface70
MergePolicy2

capabilities-and-models133

CapabilitySupport100
Modality7
ModelProviderProduct7
ModelProviderVersion7
ProcessDescriptor2
TransportProtocol10

compute116

APIErrorClass3
AgentHostTransport7
CapacityCascadeSignal2
MCPTransport4
ModelFamily23
ModelTransportProtocol12
ModelVersion49
Provider12
TranscriptIngressEndpoint1
TransportClient2
TransportProxy1

lifecycle106

capabilities85

Capability74
InstallMethod11

wiki44

Page44

security21

FilesystemSafetyInvariant3
HarnessHardeningGuidance3
OutputGuard5
OutputModeChange2
OutputStyle2
PermissionDenialReason3
SecretHandlingPolicy3

stack-layers11

Layer11

context-engineering8

BackgroundConsolidation2
CompactionPolicy2
MemoryHierarchy2
ProactiveSurface2

trust5

TrustLevel5

HomebenchmarksEvalRun

EvalRun

1 of 70 records

Active filters

testSetId: test-set:truthful-qa-mc x clear all

configHash

sha256:placeholder-gpt-5-evalplus2
sha256:placeholder-qwen-2-5-72b-mmlu1
sha256:placeholder-qwen-2-5-72b-humaneval1
sha256:placeholder-qwen-2-5-coder-32b-humaneval1
sha256:placeholder-qwen-2-5-coder-32b-lcb1
sha256:placeholder-qwen-2-5-coder-32b-mbpp1
sha256:placeholder-claude-haiku-4-5-swe-bench-verified1
sha256:placeholder-claude-haiku-4-5-gpqa1
sha256:placeholder-claude-sonnet-4-6-human-eval1
sha256:placeholder-claude-sonnet-4-6-mmlu1
sha256:placeholder-claude-sonnet-4-5-bfcl-v31
sha256:placeholder-claude-opus-4-5-gpqa-diamond1

target

model:gpt-5@current9
model:claude-sonnet-4-5@current8
model:gemini-2-5-pro@current6
model:claude-opus-4-5@current5
model:qwen-2-5-coder-32b@current3
model:deepseek-v3@current3
model:deepseek-r1@current3
model:llama-4-405b-instruct@current3
model:llama-3-1-405b-instruct@current3
model:qwen-2-5-72b-instruct@current2
model:claude-haiku-4-5@current2
model:claude-sonnet-4-6@current2

targetId

model:gpt-5@current9
model:claude-sonnet-4-5@current8
model:gemini-2-5-pro@current6
model:claude-opus-4-5@current5
model:qwen-2-5-coder-32b@current3
model:deepseek-v3@current3
model:deepseek-r1@current3
model:llama-4-405b-instruct@current3
model:llama-3-1-405b-instruct@current3
model:qwen-2-5-72b-instruct@current2
model:claude-haiku-4-5@current2
model:claude-sonnet-4-6@current2

runAt

2025-09-29T00:00:00Z13
2025-08-07T00:00:00Z9
2025-06-17T00:00:00Z7
2024-07-23T00:00:00Z6
2024-11-12T00:00:00Z3
2024-12-26T00:00:00Z3
2025-01-20T00:00:00Z3
2024-09-19T00:00:00Z2
2025-10-15T00:00:00Z2
2025-11-15T00:00:00Z2
2024-12-06T00:00:00Z2
2024-07-24T00:00:00Z2

benchmarkId

benchmark:mmlu16
benchmark:swe-bench-verified12
benchmark:human-eval10
benchmark:gpqa8
benchmark:livecodebench3
benchmark:bigcode-evalplus3
benchmark:math3
benchmark:berkeley-function-calling2
benchmark:gsm8k2
benchmark:mbpp1
benchmark:os-world1
benchmark:truthful-qa1

runBy

anthropic16
openai11
google-deepmind9
meta7
deepseek6
qwen-team5
mistral4
evalplus-leaderboard3
berkeley-gorilla2
google2
@a5c-ai/team2
artificial-analysis1

testSetId

test-set:swe-bench-verified-2024-1230
test-set:gpqa-diamond-20248
test-set:bfcl-v32
test-set:truthful-qa-mc1
test-set:gaia-validation1

Sort:id-asc id-desc name-asc name-desc

id	displayName	cluster
eval-run:truthful-qa.claude-opus-4-5.2025-09	eval-run:truthful-qa.claude-opus-4-5.2025-09	benchmarks