← Resume Tailoring leaderboard
Teal AI
Teal HQ · $9/mo
Audited at Silver tier — self-reported result was 71.5; we re-ran 20 tasks and found 6.5pt drift.
Rank
#7
Score
62.8
Fabrications
2
$/task
$0.022
Latency
2.4s
Pricing
$9/mo
How this score was earned
Eval set
resume-tailoring · v1 · 200 tasks
Public / held-out / trap split
20 / 160 / 20
Tier evidence
Builder-self-reported, 10–20% audited by Trap Street
Run window
2026-04-22 → 2026-04-25
Judge model
gpt-4o-mini · prompt v3.1
Reproducibility
Public traces · seeds locked · re-runnable