Unverified50% confidenceFactExact time
The author's experience: reasoning models typically win on only 12% of tasks and lose on the economics of the remaining 88%.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn math tasks, the accuracy was 79% when the model wrote out reasoning steps, and only 11% when it gave a bare number.76% similarUnverifiedIn 11 of the 12 models, between 87.5% and 100% of capitulation cases stopped at the exact wrong number provided by the user, meaning capitulation typically involves switching sides entirely.73% similarUnverifiedRanked by question difficulty, persistence rate was 91.4% on the 60 questions that all models answered correctly, but only 73.5% on the 52 questions that at least one model got wrong, indicating that sycophancy tracks uncertainty.72% similarUnverifiedAnthropic's research shows that even mild alignment training can cause a 2–8 percentage point decline in model performance on certain reasoning-intensive tasks.72% similarUnverified传统的成功率指标难以全面反映策略的鲁棒性，一个策略可能在90%的常规任务中表现出色却在剩余10%的关键场景中出现灾难性失败72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1038492API
curl https://kongchang.com/api/v1/knowledge/claims/1038492MCP
get_claim(id=1038492)