AA index(max 100 points):

ECI(logarithmic scale):

AA index(max 100 points):

ECI(logarithmic scale):

| № | Пользователь | Рейтинг |
|---|---|---|
| 1 | Kevin114514 | 3722 |
| 2 | Benq | 3676 |
| 3 | jiangly | 3640 |
| 4 | turmax | 3450 |
| 5 | tourist | 3408 |
| 6 | strapple | 3360 |
| 7 | Um_nik | 3354 |
| 8 | squareOf105 | 3348 |
| 9 | maroonrk | 3196 |
| 10 | idontwannadothis…e | 3191 |
| Страны | Города | Организации | Всё → |
| № | Пользователь | Вклад |
|---|---|---|
| 1 | Qingyu | 153 |
| 2 | maroonrk | 151 |
| 2 | nik_exists | 151 |
| 4 | maspy | 149 |
| 5 | AmShZ | 146 |
| 6 | Um_nik | 143 |
| 7 | Errichto | 139 |
| 8 | adamant | 135 |
| 9 | BledDest | 134 |
| 10 | cry | 130 |
| Название |
|---|



While AI progress is indeed staggering, AA is one of the worst metrics to extrapolate upon/draw conclusions from, and your use of it just exposes the larp.
Can you share a better metric?
I will recalculate
ECI, while also imperfect, is better. Labs have started sharing numbers on internal benchmarks (which are likely more meaningful) but there aren't enough datapoints for these to confidently extrapolate from.
Do Not Reproduce
dw im a stone cold truecel
added.
To be honest, I am just so disappointed with GPT 6.2 that I decide to use Gemini instead.
it is still smarter than you
Auto comment: topic has been updated by GomerDoGo (previous revision, new revision, compare).