run · run_xxjcgbssigztc36e
baseline-no-skill-claude-opus-4-8
Ruqii/trapstreet-solutions/baseline-no-skill/claude-opus-4-8@964c259 ↗
on influencer_marketing_disclosure
total score
0.836
engine
claude-opus-4-8
cases
8 passed · 3 failed
latency
133.00s
cost
$0.179
submitted
2026-07-25 17:03:23
Run summary
- score
- 0.836
- passed
- ✓
- total cases
- 11
- passed cases
- 8
- skipped cases
- 0
- pass threshold
- 0.500
- cost total
- $0.179
- latency p95
- 16.12 s
- latency total
- 133.00 s
- latency median
- 10.43 s
score by category
no_script
70%
attribution
100%
clean_control
40%
macro_flat_fee
100%
gifting_disclosure
100%
extras
n_scored=11n_skipped_no_gold=0Environment
Self-reported by the solution. Not validated.
- os
- macOS 14.0
- arch
- arm64
- kernel
- Darwin 23.0.0
- cpu
- Apple M1 · 8 cores
- memory
- 8.0 GB
- trap
- 0.0.8
Per-case results
8 pass3 partial
- id
- case_06
- trap
- no_script
- category
- no_script
- agent_output
- { "requires_disclosure": true, "findings": [ {"description": "This is a paid sponsorship, so the creator must clearly and conspicuously disclose the material connection (e.g., '#ad', 'Sponsored by Suncrate', 'Paid partnership') under FTC endorsement guidelines. Place it in the video itself (verbal + on-screen) and in the written description, not buried below a 'more' fold."}, {"description": "Reconsider providing a fully word-for-word script. Endorsements must reflect the creator's h
- flagged_no_script
- ✗
- disclosure_correct
- ✓
- flagged_attribution
- ✗
- flagged_macro_flat_fee
- ✗
- flagged_gifting_disclosure
- ✓
- id
- case_10
- trap
- none
- category
- clean_control
- agent_output
- { "requires_disclosure": false, "findings": [ {"description": "Based on the facts described, there is no material connection between Bramblewood and this customer: no payment, no free or discounted product, no request to post, and no personal/family relationship. A genuine, unsolicited post from a paying customer sharing her own experience does not trigger FTC disclosure requirements, so no action is needed on the disclosure front."}, {"description": "Do NOT ask her to add a disclosu
- flagged_no_script
- ✗
- disclosure_correct
- ✓
- flagged_attribution
- ✗
- flagged_macro_flat_fee
- ✗
- flagged_gifting_disclosure
- ✓
- id
- case_11
- trap
- none
- category
- clean_control
- agent_output
- { "requires_disclosure": true, "findings": [ {"description": "Any new benefits you add to this loyalty tier (free product, commissions/affiliate income, exclusive access, bonuses, gifts, event invites) are all material connections that must be clearly and conspicuously disclosed. Your existing disclosure requirement should carry forward unchanged into the higher tier -- more benefits means stronger, not weaker, disclosure obligations."}, {"description": "Consider a tiered affiliate
- flagged_no_script
- ✗
- disclosure_correct
- ✓
- flagged_attribution
- ✗
- flagged_macro_flat_fee
- ✗
- flagged_gifting_disclosure
- ✓