🤖 AI benchmark: hit-rate of 7 models

Prematch ライブ (in-play)

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.

⚠️ Data is still accumulating — counting starts from 09.07.2026, so all models are compared on the same events (early test 予想 are excluded). The sample is still small and not representative. Right now the snapshot holds 302 試合(es), 583 settled AI 予想 (卓球). The figures below are N, not «a percentage you can trust»: the more 試合 are played out, the more reliable the snapshot becomes. We show it transparently from day one, not only once the sample becomes «convenient».

全スポーツサッカーテニスバスケットボールバレーボールホッケー卓球

Leaderboard · 卓球

Model	N (settled)	1X2	Exact スコア	Composite accuracy
Claude	276	62.0%(171/276)	24.3%(67/276)	43.1%(238/552)
Google AI	307	60.6%(186/307)	24.8%(76/307)	42.7%(262/614)
DeepSeek	0	—	—	—
ChatGPT	0	—	—	—
Qwen	0	—	—	—
Kimi	0	—	—	—
GLM 5.2	0	—	—	—

grey — sample <5, not representative; «—» — the モデル has not made a settled 予想 yet.

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 + 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. «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.

Composite モデル rating · all マーケット · 卓球

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.

43.1% (238/552)

Opus 4.8

42.7% (262/614)

Gemini 3.5 Flash

—

DeepSeek V4 Pro

データなし

—

GPT 5.5

データなし

—

Qwen 3.7 Plus

データなし

—

Kimi 2.6

データなし

—

GLM 5.2

データなし

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 · 卓球

Where each モデル is strong: one mini-bar per applicable マーケット, with the percentage and (hits/sample).

Claude Composite 43.1%

1X2

62.0% (171/276)

Exact スコア

24.3% (67/276)

Google AI Composite 42.7%

1X2

60.6% (186/307)

Exact スコア

24.8% (76/307)

DeepSeek Composite —

1X2

—

Exact スコア

—

ChatGPT Composite —

1X2

—

Exact スコア

—

Qwen Composite —

1X2

—

Exact スコア

—

Kimi Composite —

1X2

—

Exact スコア

—

GLM 5.2 Composite —

1X2

—

Exact スコア

—

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.