MODELDRIFT.WATCH

Question 1

Facts and formats · the question whether 91 is prime · paired with Question 2

Sent verbatim, every day

Is 91 a prime number? Think step by step and then answer "[Yes]" or "[No]".

  1. GPT

    answered 24 of 61 days · 37 no response

    Right on 24 of the 24 days it answered.

  2. Claude

    answered 23 of 61 days · 38 no response

    Right on 23 of the 23 days it answered.

  3. Gemini

    answered 23 of 61 days · 38 no response

    Right on 23 of the 23 days it answered.

  • No response
The whole record, 61 daysShowHideThe rails above show the last 30 days

GPT

SEP 10OCT 9

OCT 10NOV 8

NOV 9NOV 9

Claude

SEP 10OCT 9

OCT 10NOV 8

NOV 9NOV 9

Gemini

SEP 10OCT 9

OCT 10NOV 8

NOV 9NOV 9

Every answer

Every model gave the same answer every day it answered.

  1. GPT“No” on 24 of 61 days, right every time
  2. Claude“No” on 23 of 61 days, right every time
  3. Gemini“No” on 23 of 61 days, right every time
Day by dayShowHideThe start of each day’s answer, newest first

  1. Nov 9

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  2. Nov 8

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  3. Nov 7

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  4. Nov 6

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  5. Nov 5

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  6. Nov 4

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  7. Nov 3

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  8. Nov 2

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  9. Nov 1

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  10. Oct 31

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  11. Oct 30

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  12. Oct 29

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  13. Oct 28

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  14. Oct 27

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  15. Oct 26

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  16. Oct 25

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  17. Oct 24

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  18. Oct 23

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  19. Oct 22

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  20. Oct 21

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  21. Oct 20

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  22. Oct 19

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  23. Oct 18

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  24. Oct 17

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  25. Oct 16

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  26. Oct 15

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  27. Oct 14

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  28. Oct 13

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  29. Oct 12

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  30. Oct 11

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  31. Oct 10

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  32. Oct 9

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  33. Oct 8

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  34. Oct 7

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  35. Oct 6

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  36. Oct 5

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  37. Oct 4

    1. GPTNo response: the request failed, so this day is a gap
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  38. Oct 3

    1. GPT[No]
    2. ClaudeStep 1: Check if 91 is even.…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers up to its square root.…

  39. Oct 2

    1. GPT[No]
    2. ClaudeStep-by-step reasoning…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  40. Oct 1

    1. GPT[No]
    2. ClaudeStep-by-step check…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers up to its square root.…

  41. Sep 30

    1. GPT[No]
    2. ClaudeStep 1: Check what 91 is.…
    3. GeminiTo determine if 91 is a prime number, we need to check if it has any positive divisors other than 1 and itself. We can do this by testing…

  42. Sep 29

    1. GPT[No]
    2. ClaudeStep 1: Understand what's being asked.…
    3. GeminiTo determine if 91 is a prime number, we need to check if it has any positive divisors other than 1 and itself. We only need to test prime…

  43. Sep 28

    1. GPT[No]
    2. ClaudeStep-by-step check…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  44. Sep 27

    1. GPT[No]
    2. ClaudeStep-by-step check…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  45. Sep 26

    1. GPT[No]
    2. ClaudeStep 1: Check what 91 is.…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  46. Sep 25

    1. GPT[No]
    2. ClaudeStep 1: Check what a prime number requires.…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  47. Sep 24

    1. GPT[No]
    2. ClaudeNo response: the request failed, so this day is a gap
    3. GeminiNo response: the request failed, so this day is a gap

  48. Sep 23

    1. GPT[No]
    2. ClaudeStep 1: Understand what's needed.…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  49. Sep 22

    1. GPT[No]
    2. ClaudeStep 1: Understand what's needed…
    3. GeminiTo determine if 91 is a prime number, we need to check if it has any positive divisors other than 1 and itself. We can do this by testing…

  50. Sep 21

    1. GPT[No]
    2. ClaudeStep 1: Check what "prime" requires.…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers up to its square root. The square root of 91 is…

  51. Sep 20

    1. GPT[No]
    2. ClaudeStep 1: Check what 91 is.…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  52. Sep 19

    1. GPT[No]
    2. ClaudeStep-by-step check…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  53. Sep 18

    1. GPT[No]
    2. ClaudeStep-by-step check…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  54. Sep 17

    1. GPT[No]
    2. ClaudeStep 1: Check the size of the number.…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  55. Sep 16

    1. GPT[No]
    2. ClaudeStep-by-step reasoning…
    3. GeminiTo determine if 91 is a prime number, we need to check if it has any positive divisors other than 1 and itself.…

  56. Sep 15

    1. GPT[No]
    2. ClaudeStep 1: Check what 91 is.…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (which is roughly…

  57. Sep 14

    1. GPT[No]
    2. ClaudeStep 1: Check what 91 is.…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  58. Sep 13

    1. GPT[No]
    2. ClaudeStep 1: Find the square root bound…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  59. Sep 12

    1. GPT[No]
    2. ClaudeStep 1: Check what 91 is.…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (the square root of…

  60. Sep 11

    1. GPT[No]
    2. ClaudeStep 1: Check what 91 is divisible by.…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers up to the square root of 91 (which is…

  61. Sep 10

    1. GPT[No]
    2. ClaudeStep 1: Check what 91 is.…
    3. GeminiTo determine if 91 is a prime number, we can check if it is divisible by any prime numbers smaller than its square root (which is roughly…
Why this question is in the batteryShowHideWhat it tests, how it is scored
Why
91 looks prime but is 7 × 13, so a model that goes by the look of a number gets it wrong.
Pair
Question 1, the one that only looks prime · Question 2, the one that is prime
Correct if
the response answers [No] (91 = 7 × 13)
Format ok if
the response ends with a [Yes]/[No] bracket