GET /experimental/eval-runs/{id}/stats

Admin Keys3

Agent Logs1

AgentSignals1

API Keys3

Auth2

Badges1

Billing7

ByoProvider4

Capacity3

Claude Marketplace9

CLI2

ClientState1

Code Review3

Context14

Environments6

Evals13

get/experimental/eval-runs
get/experimental/eval-runs/{id}
patch/experimental/eval-runs/{id}
get/experimental/eval-runs/{id}/stats
get/experimental/eval-run-comparisons
get/experimental/eval-runs/{id}/debug
get/experimental/eval-runs/{id}/solutions/{solutionId}/files
post/experimental/eval-runs-v2
post/experimental/eval-runs-v2:check
get/experimental/eval-runs/agents
get/experimental/eval-runs/repo-results
post/experimental/eval-scenarios/generate
post/experimental/eval-runs/{id}/retry

Fix Runs4

Generation5

InstallPolicy4

Integrations15

Launch Runs9

LLM4

ManagedProjectPolicy3

Orgs53

Policy5

Projects8

PublishPolicy3

Repos1

Review Runs4

Reviews3

Schedules8

Search3

Security Review Runs2

SkillInventory1

Skills14

Tasks9

Tiles16

Users13

Workflows1

Workspaces32

Evals

Returns aggregated stats per (scenario × variant) group for an eval run. Every numeric quantity carries the full distribution suite — Min, Q1, Median, Mean, Q3, Max, StdDev — never bare means.

get/experimental/eval-runs/{id}/stats

Path parameters

idstring uuid required

Response

Default Response

Path parameters

Response

Changes