Unverified50% confidenceFactExact time
Under faults, the 120B model did not retain a higher proportion of its fault-free score than the 20B model; the p = 0.96 for the fault-tolerance-rate model indicates that the scale difference is not statistically significant.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedB1 made 181 predictions with confidence no lower than 0.9, of which 1 was wrong; B2 made 188, of which 2 were wrong; a better average does not automatically mean fewer high-confidence errors, and 0.9 is not a ready-made production threshold.74% similarUnverifiedIn a test of 119 pairs of "near-identical questions", at the 0.81 threshold 62% of modified questions incorrectly hit; even raised to 0.90, 25% still hit; the hit rate for genuine synonymous rewrites dropped from 39% to 4%.74% similarUnverifiedThe only real advantage of 120B over 20B is more reliable orchestration, but even this did not solve the deeper reliability problem it was supposed to solve.74% similarUnverifiedSetting an absolute failure count ceiling for small-sample slices is more robust than setting a percentage threshold and is insensitive to sample size74% similarUnverifiedThe NPV of definitive benign cases (0.73) still lags behind the malignant precision (0.94), indicating that the model has insufficient confidence in ruling out malignancy.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1098597API
curl https://kongchang.com/api/v1/knowledge/claims/1098597MCP
get_claim(id=1098597)