eval.qa · aif · dashboard

AIF dashboard

Append-only JSONL store. Refresh after submitting a form to see new records.

380
total evals
3.78
avg rating
0
violating safety
-
human vs LLM Δ
3
rater types

By rater type

human 354
end_user 25
llm_judge 1

By modality

text 1
chat 337
agent 5
rag 9
unknown 28

Recent evals

whenraterleveltemplatemodalitytaskratingsafetytags
2026-11-06T16:05 [email protected] human enduser chat ad-hoc 2 clean
2026-11-04T14:03 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-11-03T09:50 [email protected] human bugreport chat ad-hoc - clean
2026-11-03T08:14 [email protected] human questions chat ad-hoc - clean
2026-11-03T08:14 [email protected] human enduser chat ad-hoc 4 clean
2026-10-27T07:35 [email protected] human enduser chat ad-hoc 4 clean
2026-10-27T07:30 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
2026-10-27T07:27 [email protected] human enduser chat ad-hoc 3 clean
2026-10-27T04:42 [email protected] human questions chat ad-hoc - clean
2026-10-27T04:41 [email protected] human bugreport chat ad-hoc - clean
2026-10-27T04:41 [email protected] human enduser chat ad-hoc 4 clean
2026-10-26T04:58 [email protected] human questions chat ad-hoc - clean
2026-10-23T15:28 [email protected] human enduser chat ad-hoc 4 clean
2026-10-23T14:33 [email protected] human enduser chat ad-hoc 3 clean
2026-10-23T14:21 [email protected] human enduser chat ad-hoc 3 clean
2026-10-23T14:04 [email protected] human enduser chat ad-hoc 3 clean
2026-10-23T13:54 [email protected] human enduser chat ad-hoc 3 clean
2026-10-23T13:47 [email protected] human enduser chat ad-hoc 3 clean
2026-10-23T13:00 [email protected] human enduser chat ad-hoc 3 clean
2026-10-23T12:53 [email protected] human questions chat ad-hoc - clean
2026-10-23T12:53 [email protected] human bugreport chat ad-hoc - clean
2026-10-23T12:51 [email protected] human enduser chat ad-hoc 4 clean
2026-10-23T12:09 [email protected] human enduser chat ad-hoc 3 clean
2026-10-23T12:05 [email protected] human enduser chat ad-hoc 3 clean
2026-10-23T12:03 [email protected] human enduser chat ad-hoc 5 clean helpful accurate safe
+ New evaluation Eval Army profile Embed SDK stats JSON demo home