🤖 AI benchmark: hit-rate of 7 models
Seven external AI models (Hermes contour) independently analyze the same 試合 — predicting the 結果 (1X2), total (オーバー/アンダー), both チーム to スコア (BTTS) and the exact スコア. Here we honestly compare their 予想 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 · サッカー
| Model | N (settled) | 1X2 | ダブルチャンス (1X) | Total ゴール | BTTS | Exact スコア | 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
|
889 | 54.0%(480/889) | 77.5%(689/889) | 66.1%(508/769) | 57.9%(446/770) | 17.0%(131/772) | 48.9%(1565/3200) |
 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) |
 Google AI
|
1115 | 52.1%(580/1114) | 74.9%(834/1114) | 60.1%(645/1074) | 54.7%(494/903) | 11.6%(129/1109) | 44.0%(1848/4200) |
 GLM 5.2
|
406 | 50.2%(204/406) | 74.4%(302/406) | 55.7%(221/397) | 52.8%(209/396) | 9.8%(39/398) | 42.1%(673/1597) |
 Qwen
|
356 | 48.9%(174/356) | 75.0%(267/356) | 52.9%(176/333) | 52.3%(171/327) | 7.8%(26/335) | 40.5%(547/1351) |
 Kimi
|
343 | 49.3%(169/343) | 73.8%(253/343) | 50.7%(155/306) | 48.5%(149/307) | 9.7%(30/309) | 39.8%(503/1265) |
grey — sample <5, not representative; «—» — the モデル has not made a settled 予想 yet.
ダブルチャンス (1X) — the same ピック counts as a 勝利 if the chosen side won or the 試合 drew. Of the 1X2 losses in football/hockey: 752 draws, 797 underdog (total settled 1X2 ピック in these sports: 3212, double chance combined 75.2% (2415/3212)). The models almost always take the favorite and don't bet on a 引き分け — double chance shows how many bets are eaten specifically by draws.
Composite accuracy — the share of correct 予想 横断 all 表示 マーケット together: (sum of correct ピック) ÷ (sum of all settled ピック) 横断 the マーケット 1X2 + Total ゴール + BTTS + Exact スコア. Each マーケット-ピック weighs equally. This is hit-rate, not profitability — for money/ROI by モデル see /ai-agent. Total: a push (スコア exactly ライン上) is excluded from the denominator. BTTS is checked against whether both チーム scored. «Exact スコア» — the full final スコア was guessed correctly (H and A matched); 予想 with no recognized スコア do not count toward the denominator. ダブルチャンス (1X): a ピック counts as a 勝利 if the chosen side won OR it was a 引き分け — it accounts for frequent draws that «eat» bets on the favorite. This metric is informational and is not included in composite accuracy.
Composite モデル rating · all マーケット · サッカー
Bar height = the モデル's composite accuracy 横断 all applicable マーケット 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 マーケット · サッカー
Where each モデル is strong: one mini-bar per applicable マーケット, with the percentage and (hits/sample).
ChatGPT
Composite 49.3%
Claude
Composite 48.9%
DeepSeek
Composite 44.4%
Google AI
Composite 44.0%
GLM 5.2
Composite 42.1%
Qwen
Composite 40.5%
Kimi
Composite 39.8%
The モデル's favorite by 1X2 = the max of P1/X/P2 in its probabilities; for sports without a 引き分け (tennis, volleyball, etc.) the «X» option doesn't participate. grey — sample <5, not representative. Not betting advice.