🤖 AI benchmark: hit-rate of 7 models
Seven external AI models (Hermes contour) independently analyze the same partite — predicting the esito (1X2), total (Over/Under), both squadre to punteggio (BTTS) and the exact punteggio. Here we honestly compare their pronostici against the real result after the final whistle and combine everything into a single accuracy rating. An informational and analytical snapshot, not betting advice.
Leaderboard
| Model | N (settled) | 1X2 | Doppia chance (1X) | Exact punteggio | Composite accuracy |
|---|---|---|---|---|---|
 ChatGPT
|
263 | 65.0%(171/263) | 74.6%(47/63) | 17.2%(35/203) | 44.2%(206/466) |
 Claude
|
2138 | 61.4%(1312/2138) | 77.7%(593/763) | 21.9%(407/1859) | 43.0%(1719/3997) |
 Kimi
|
1109 | 60.8%(674/1109) | 73.8%(253/343) | 20.3%(196/964) | 42.0%(870/2073) |
 Google AI
|
2778 | 60.4%(1676/2776) | 74.8%(717/958) | 20.1%(550/2736) | 40.4%(2226/5512) |
 GLM 5.2
|
1285 | 59.5%(765/1285) | 74.4%(302/406) | 19.5%(246/1261) | 39.7%(1011/2546) |
 DeepSeek
|
175 | 60.6%(106/175) | 56.1%(23/41) | 18.5%(32/173) | 39.7%(138/348) |
 Qwen
|
1237 | 59.3%(733/1237) | 75.0%(267/356) | 16.8%(196/1166) | 38.7%(929/2403) |
grey — sample <5, not representative; «—» — the model has not made a settled pronostico yet.
Doppia chance (1X) — the same pronostico counts as a vittoria if the chosen side won or the partita drew. Of the 1X2 losses in football/hockey: 671 draws, 728 underdog (total settled 1X2 pronostici in these sports: 2930, double chance combined 75.2% (2202/2930)). The models almost always take the favorite and don't bet on a pareggio — double chance shows how many bets are eaten specifically by draws.
Composite accuracy — the share of correct pronostici su all mostrato mercati together: (sum of correct pronostici) ÷ (sum of all settled pronostici) su the mercati 1X2 + Exact punteggio. Each mercato-pronostico weighs equally. This is hit-rate, not profitability — for money/ROI by model see /ai-agent. «Exact punteggio» — the full final punteggio was guessed correctly (H and A matched); for tennis, sets are compared; pronostici with no recognized punteggio do not count toward the denominator. Doppia chance (1X): a pronostico counts as a vittoria if the chosen side won OR it was a pareggio — it accounts for frequent draws that «eat» bets on the favorite. This metric is informational and is not included in composite accuracy. On «Tutti gli sport» we don't show total and BTTS — they're tied to the sport and make no sense in a mixed pool.
Composite model rating · all mercati
Bar height = the model's composite accuracy su all applicable mercati 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.
Accuracy by mercato
Where each model is strong: one mini-bar per applicable mercato, with the percentage and (hits/sample).
ChatGPT
Composite 44.2%
Claude
Composite 43.0%
Kimi
Composite 42.0%
Google AI
Composite 40.4%
GLM 5.2
Composite 39.7%
DeepSeek
Composite 39.7%
Qwen
Composite 38.7%
The model's favorite by 1X2 = the max of P1/X/P2 in its probabilities; for sports without a pareggio (tennis, volleyball, etc.) the «X» option doesn't participate. grey — sample <5, not representative. Not betting advice.