Seven external AI models (Hermes contour) independently analyze the same แมตช์ — predicting the ผล (1X2), total (สูง/ต่ำ), both ทีม to สกอร์ (BTTS) and the exact สกอร์. Here we honestly compare their ทายผล against the real result after the final whistle and combine everything into a single accuracy rating. An informational and analytical snapshot, not betting advice.
| Model | N (settled) | 1X2 | Exact สกอร์ | Composite accuracy |
|---|---|---|---|---|
|
|
63 | 65.1%(41/63) | 31.9%(15/47) | 50.9%(56/110) |
|
|
18 | 66.7%(12/18) | 18.2%(2/11) | 48.3%(14/29) |
|
|
98 | 65.3%(64/98) | 19.5%(15/77) | 45.1%(79/175) |
|
|
13 | 76.9%(10/13) | 7.7%(1/13) | 42.3%(11/26) |
|
|
124 | 64.5%(80/124) | 19.4%(24/124) | 41.9%(104/248) |
|
|
82 | 69.5%(57/82) | 7.9%(6/76) | 39.9%(63/158) |
|
|
82 | 65.9%(54/82) | 11.0%(9/82) | 38.4%(63/164) |
grey — sample <5, not representative; «—» — the โมเดล has not made a settled ทายผล yet.
Composite accuracy — the share of correct ทายผล ทั่ว all แสดง ตลาด together: (sum of correct ทายผล) ÷ (sum of all settled ทายผล) ทั่ว the ตลาด 1X2 + Exact สกอร์. Each ตลาด-ทายผล weighs equally. This is hit-rate, not profitability — for money/ROI by โมเดล see /ai-agent. «Exact สกอร์» — the full final สกอร์ was guessed correctly (H and A matched); ทายผล with no recognized สกอร์ do not count toward the denominator.
Bar height = the โมเดล's composite accuracy ทั่ว all applicable ตลาด on the current sample. Sorted from best to worst.
Bars are AI models by version; grey/dimmed — sample <5, not representative. The snapshot is informational, not betting advice.
Where each โมเดล is strong: one mini-bar per applicable ตลาด, with the percentage and (hits/sample).
The โมเดล's favorite by 1X2 = the max of P1/X/P2 in its probabilities; for sports without a เสมอ (tennis, volleyball, etc.) the «X» option doesn't participate. grey — sample <5, not representative. Not betting advice.