DeepSeek R1 (2 articles)

DeepSeek R1 Stability Plummets 22 Points: The Truth Behind Complete Failure on Simple Judgment Questions

DeepSeek R1's stability score crashed from 53.7 to 31.6 points this week, with the model failing basic judgment questions like whether water can boil at 101°C under standard pressure, raising serious concerns about its reliability.

Technical Concerns Behind DeepSeek R1's 22-Point Stability Plunge

DeepSeek R1 shows extreme performance polarization in this week's evaluation: programming capability soared 47.4 points while stability plummeted 22.1 points, revealing critical trade-offs in model optimization.