algorithmic-art (Anthropic) vs emails (coreyhaines31/marketingskills)
algorithmic-art (Anthropic)
22.5 / 30
SituationalSafe
algorithmic-art: every arm passes the rule checks (4.5 / 4.8 / 5.0), but only the skill and a one-sentence prompt write a real philosophy document; the skill costs 2x the tokens
- SOTAPass
emails (coreyhaines31/marketingskills)
24.0 / 30
SituationalSafe
emails (marketingskills): ties plain Codex at 5.0/5 on three email-sequence tasks, at 1.5x the tokens
- SOTAPass