SPICE

Hub › Lists › EvalResults

Eval results - graded verdicts on capability output, one row per run. About this list · Site contents

EvalResultsCheck items, then use the ITEMS tab; list tools are on the LIST tab.
Manage
Standard ViewBoard: EvalTierBoard: EvalOutcome
View Format
Manage Views
RSS FeedExport to Excel
Share & Track
List SettingsRecycle Bin
Settings
This siteDocumentsDropOffLibraryRoutingRulesDocumentsActorsCopilotsInboxConversationsSavedSearchesHealthIssuesEvalResultsWorkflowHistory
Clear all
Title: Eval Eval.DeepResearch: Pass (Quality) x
Eval Eval.CatalogExtract.SolarPanel: Fail (Quality) (2)Eval Eval.CatalogExtract.SolarPanel: Pass (Quality) (1)Eval Eval.DailyBrief: Fail (Quality) (7)Eval Eval.DailyBrief: Pass (Quality) (19)Eval Eval.DeepResearch: Fail (Quality) (9)Eval Eval.DeepResearch: Pass (Quality) (2)Eval Eval.HealthReview: Degraded (Quality) (8)Eval Eval.HealthReview: Fail (Quality) (10)Eval Eval.HealthReview: Pass (Deterministic) (1)Eval Eval.HealthReview: Pass (Quality) (2)Eval Eval.ResearchFinding: Fail (Quality) (5)
Eval.DeepResearch (2)
Tool.DeepResearch (2)
Quality (2)
Pass (2)
2 items of 2All lists
ContentType: ContentType.EvalResult   Lineage: ContentType.Item -> ContentType.EvalResult
Title * (filtered)
CreatedAt
Author
EvalId *
EvalTarget *
EvalTier *
EvalOutcome *
EvalScore
EvalFailedAssertions
Modified
Eval Eval.DeepResearch: Pass (Quality)
...
 System Account (SPICE.Web) Eval.DeepResearch Tool.DeepResearch Quality Pass 100 2026-08-04T14:28:07.8298517
Eval Eval.DeepResearch: Pass (Quality)
...
 System Account (SPICE.Web) Eval.DeepResearch Tool.DeepResearch Quality Pass 100 2026-08-04T14:12:05.2601771