Models
Every provider:model of the pipeline's LLM calls and of the eval scorecard: how a model scores on the datasets next to how it behaves in production. Eval runs record the model only; the provider is inferred (claude-* → anthropic, else groq).
anthropic:anthropic:claude-opus-5-5
Pipeline runs: none in the window
Eval runs: review 39000563980-review ✓, review 38994398984-review ✓
anthropic:claude-haiku-5-5
Pipeline runs: 41155445917-1, 41155442127-1, 41155366230-1, 41155350819-1, 41155255528-1, 41155239149-1, 41154791089-1, 41154746517-1, 41154727113-1, 41154706629-1, 41154674007-1, 41154646413-1, 41154619935-1, 41154586154-1, 41153017065-1, 41153005971-1, 41152994561-1, 41152985325-1, 41152977074-1, 41152967147-1
Eval runs: none on the scorecard
anthropic:claude-opus-5-5
Pipeline runs: 38848182099-1
Eval runs: none on the scorecard
anthropic:claude-sonnet-5-5
Pipeline runs: 41155321170-1, 41154652610-1, 41151936838-1, 41112867211-1, 41112012092-1, 41111691401-1, 41111157380-1, 41108652433-1, 41075772544-1, 41074790503-1, 41073850373-1, 40776573850-1, 40774479747-1, 40766397145-1, 40754734782-1, 40754964443-1, 40753946966-1, 40753415508-1, 40752783973-1, 40751320947-1
Eval runs: none on the scorecard
groq:groq:openai/gpt-oss-120b
Pipeline runs: none in the window
Eval runs: validation 39260535854-validation ✕, validation 38847780079-validation ✓, validation 38271632735-validation ✕, validation 37173049724 ✓
groq:openai/gpt-oss-120b
Pipeline runs: 41154713645-1, 41111383676-1, 40755480973-1, 40755215086-1, 40754918718-1, 40563001144-1, 40251235102-1, 40194269858-1, 40159225402-1, 39842401383-1, 39841571957-1, 39841247035-1, 39542338480-1, 39540372924-1, 39540071112-1, 39536847321-1, 39536378113-1, 39533424594-1, 39514964984-1, 39514660585-1
Eval runs: none on the scorecard