Unverified50% confidenceFactExact time
The test ran a total of 130 variants, covering different levels of reasoning effort, called via OpenRouter with official endpoints for each lab locked in wherever possible.
1
Sources
50%
Confidence
Long-term
Relevance
10/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAn independent researcher constructed 22 multi-turn traps and 84 single-turn traps, had 10 models run through all 106 tests, and independently scored each trajectory using three methods.72% similarUnverifiedThe experiment tested 15 frontier models.70% similarUnverifiedThe test ultimately produced a sample of 174 tasks and 1,744 attempts, using an A/B comparison method with the same routing, same platform, and same time period.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/973738API
curl https://kongchang.com/api/v1/knowledge/claims/973738MCP
get_claim(id=973738)