🤖 AI benchmark: hit-rate of 7 models
Seven external AI models (Hermes contour) independently analyze the same matchs — predicting the résultat (1X2), total (Plus de/Moins de), both équipes to score (BTTS) and the exact score. Here we honestly compare their pronostics 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 | Double chance (1X) | Exact score | Composite accuracy |
|---|---|---|---|---|---|
 ChatGPT
|
263 | 65.0%(171/263) | 74.6%(47/63) | 17.2%(35/203) | 44.2%(206/466) |
 Claude
|
2170 | 61.4%(1332/2170) | 77.6%(612/789) | 21.9%(414/1891) | 43.0%(1746/4061) |
 Kimi
|
1109 | 60.8%(674/1109) | 73.8%(253/343) | 20.3%(196/964) | 42.0%(870/2073) |
 Google AI
|
2810 | 60.3%(1694/2808) | 74.7%(735/984) | 20.0%(554/2768) | 40.3%(2248/5576) |
 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 modèle has not made a settled pronostic yet.
Double chance (1X) — the same pronostic counts as a victoire if the chosen side won or the match drew. Of the 1X2 losses in football/hockey: 680 draws, 743 underdog (total settled 1X2 pronostics in these sports: 2982, double chance combined 75.1% (2239/2982)). The models almost always take the favorite and don't bet on a nul — double chance shows how many bets are eaten specifically by draws.
Composite accuracy — the share of correct pronostics sur all affiché marchés together: (sum of correct pronostics) ÷ (sum of all settled pronostics) sur the marchés 1X2 + Exact score. Each marché-pronostic weighs equally. This is hit-rate, not profitability — for money/ROI by modèle see /ai-agent. «Exact score» — the full final score was guessed correctly (H and A matched); for tennis, sets are compared; pronostics with no recognized score do not count toward the denominator. Double chance (1X): a pronostic counts as a victoire if the chosen side won OR it was a nul — it accounts for frequent draws that «eat» bets on the favorite. This metric is informational and is not included in composite accuracy. On «Tous les sports» we don't show total and BTTS — they're tied to the sport and make no sense in a mixed pool.
Composite modèle rating · all marchés
Bar height = the modèle's composite accuracy sur all applicable marchés 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 marché
Where each modèle is strong: one mini-bar per applicable marché, with the percentage and (hits/sample).
ChatGPT
Composite 44.2%
Claude
Composite 43.0%
Kimi
Composite 42.0%
Google AI
Composite 40.3%
GLM 5.2
Composite 39.7%
DeepSeek
Composite 39.7%
Qwen
Composite 38.7%
The modèle's favorite by 1X2 = the max of P1/X/P2 in its probabilities; for sports without a nul (tennis, volleyball, etc.) the «X» option doesn't participate. grey — sample <5, not representative. Not betting advice.