🤖 AI benchmark: hit-rate of 7 models
Seven external AI models (Hermes contour) independently analyze the same matches — predicting the outcome (1X2), total (Over/Under), both teams to score (BTTS) and the exact score. Here we honestly compare their predictions 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 · Football
| Model | N (settled) | 1X2 | Double chance (1X) | Total goals | BTTS | Exact score | Composite accuracy |
|---|---|---|---|---|---|---|---|
 ChatGPT
|
63 | 58.7%(37/63) | 74.6%(47/63) | 67.4%(31/46) | 59.6%(28/47) | 10.2%(5/49) | 49.3%(101/205) |
 Claude
|
950 | 53.6%(509/950) | 77.5%(736/950) | 65.7%(545/830) | 57.9%(481/831) | 17.0%(142/833) | 48.7%(1677/3444) |
 DeepSeek
|
41 | 46.3%(19/41) | 56.1%(23/41) | 61.5%(24/39) | 61.5%(24/39) | 9.8%(4/41) | 44.4%(71/160) |
 GLM 5.2
|
408 | 50.5%(206/408) | 74.5%(304/408) | 55.6%(222/399) | 52.8%(210/398) | 9.8%(39/400) | 42.2%(677/1605) |
 Google AI
|
2370 | 51.3%(1215/2369) | 74.7%(1770/2369) | 59.9%(754/1259) | 55.3%(603/1090) | 12.5%(296/2364) | 40.5%(2868/7082) |
 Qwen
|
357 | 49.0%(175/357) | 75.1%(268/357) | 52.7%(176/334) | 52.1%(171/328) | 7.7%(26/336) | 40.4%(548/1355) |
 Kimi
|
345 | 49.6%(171/345) | 73.9%(255/345) | 50.6%(156/308) | 48.5%(150/309) | 9.6%(30/311) | 39.8%(507/1273) |
grey — sample <5, not representative; «—» — the model has not made a settled prediction yet.
Double chance (1X) — the same pick counts as a win if the chosen side won or the match drew. Of the 1X2 losses in football/hockey: 1071 draws, 1130 underdog (total settled 1X2 picks in these sports: 4533, double chance combined 75.1% (3403/4533)). The models almost always take the favorite and don't bet on a draw — double chance shows how many bets are eaten specifically by draws.
Composite accuracy — the share of correct predictions across all shown markets together: (sum of correct picks) ÷ (sum of all settled picks) across the markets 1X2 + Total goals + BTTS + Exact score. Each market-pick weighs equally. This is hit-rate, not profitability — for money/ROI by model see /ai-agent. Total: a push (score exactly on the line) is excluded from the denominator. BTTS is checked against whether both teams scored. «Exact score» — the full final score was guessed correctly (H and A matched); predictions with no recognized score do not count toward the denominator. Double chance (1X): a pick counts as a win if the chosen side won OR it was a draw — it accounts for frequent draws that «eat» bets on the favorite. This metric is informational and is not included in composite accuracy.
Composite model rating · all markets · Football
Bar height = the model's composite accuracy across all applicable markets 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 market · Football
Where each model is strong: one mini-bar per applicable market, with the percentage and (hits/sample).
ChatGPT
Composite 49.3%
Claude
Composite 48.7%
DeepSeek
Composite 44.4%
GLM 5.2
Composite 42.2%
Google AI
Composite 40.5%
Qwen
Composite 40.4%
Kimi
Composite 39.8%
The model's favorite by 1X2 = the max of P1/X/P2 in its probabilities; for sports without a draw (tennis, volleyball, etc.) the «X» option doesn't participate. grey — sample <5, not representative. Not betting advice.