metaphi-ai commited on
Commit
69ab93b
Β·
verified Β·
1 Parent(s): 5ee1146

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ pinned: false
16
  | Agent | Occupation | Scale | What It Tests | Verifiers |
17
  |-------|--------|-------|------------|--------|
18
  | **[FinAgent](link)** | Credit analyst | 2,610 tasks, 26K+ PDFs | Multiple document reasoning β†’ taxonomy aware transaction categorization β†’ Business P&L construction | Binary pass/fail |
19
- | **[Enterprise Knowledge Agent](link)** | Senior business analyst | 1,220 pitch-deck tasks, 45 video tasks, 279 preference pairs | Source faitfhulness β†’ narrative arc based story-telling | Precision, Recall on citation. Subjective on video preference |
20
  | **[FigmaAgent](link)** | Senior Frontend engineer | 37 tasks, 147 expert preferences | Figma environment navigation β†’ design system creation β†’ build verification | Subjective on output preference |
21
 
22
  ## Leaderboard
 
16
  | Agent | Occupation | Scale | What It Tests | Verifiers |
17
  |-------|--------|-------|------------|--------|
18
  | **[FinAgent](link)** | Credit analyst | 2,610 tasks, 26K+ PDFs | Multiple document reasoning β†’ taxonomy aware transaction categorization β†’ Business P&L construction | Binary pass/fail |
19
+ | **[Enterprise Knowledge Agent](link)** | Senior business analyst | 1,220 pitch-deck tasks, 45 video tasks, 279 preference pairs | Source faitfhulness β†’ narrative arc based story-telling --> design coherenece| Precision, Recall on citation. Subjective on video preference |
20
  | **[FigmaAgent](link)** | Senior Frontend engineer | 37 tasks, 147 expert preferences | Figma environment navigation β†’ design system creation β†’ build verification | Subjective on output preference |
21
 
22
  ## Leaderboard