🤖 AI benchmark: hit-rate of 7 models

Prematch Na żywo (in-play)

Seven external AI models (Hermes contour) independently analyze the same mecze — predicting the wynik (1X2), total (Powyżej/Poniżej), both drużyny to wynik (BTTS) and the exact wynik. Here we honestly compare their typy 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 typy are excluded). The sample is still small and not representative. Right now the snapshot holds 298 mecz(es), 577 settled AI typy (Tenis stołowy). The figures below are N, not «a percentage you can trust»: the more mecze are played out, the more reliable the snapshot becomes. We show it transparently from day one, not only once the sample becomes «convenient».

Wszystkie sporty Piłka nożna Tenis Koszykówka Siatkówka Hokej Tenis stołowy

Leaderboard · Tenis stołowy

Model	N (settled)	1X2	Exact wynik	Composite accuracy
Claude	274	62.0%(170/274)	24.5%(67/274)	43.2%(237/548)
Google AI	303	60.4%(183/303)	25.1%(76/303)	42.7%(259/606)
DeepSeek	0	—	—	—
ChatGPT	0	—	—	—
Qwen	0	—	—	—
Kimi	0	—	—	—
GLM 5.2	0	—	—	—

grey — sample <5, not representative; «—» — the model has not made a settled typ yet.

Composite accuracy — the share of correct typy w all pokazano rynki together: (sum of correct typy) ÷ (sum of all settled typy) w the rynki 1X2 + Exact wynik. Each rynek-typ weighs equally. This is hit-rate, not profitability — for money/ROI by model see /ai-agent. «Exact wynik» — the full final wynik was guessed correctly (H and A matched); typy with no recognized wynik do not count toward the denominator.

Composite model rating · all rynki · Tenis stołowy

Bar height = the model's composite accuracy w all applicable rynki on the current sample. Sorted from best to worst.

43.2% (237/548)

Opus 4.8

42.7% (259/606)

Gemini 3.5 Flash

—

DeepSeek V4 Pro

brak danych

—

GPT 5.5

brak danych

—

Qwen 3.7 Plus

brak danych

—

Kimi 2.6

brak danych

—

GLM 5.2

brak danych

Bars are AI models by version; grey/dimmed — sample <5, not representative. The snapshot is informational, not betting advice.

Accuracy by rynek · Tenis stołowy

Where each model is strong: one mini-bar per applicable rynek, with the percentage and (hits/sample).

Claude Composite 43.2%

1X2

62.0% (170/274)

Exact wynik

24.5% (67/274)

Google AI Composite 42.7%

1X2

60.4% (183/303)

Exact wynik

25.1% (76/303)

DeepSeek Composite —

1X2

—

Exact wynik

—

ChatGPT Composite —

1X2

—

Exact wynik

—

Qwen Composite —

1X2

—

Exact wynik

—

Kimi Composite —

1X2

—

Exact wynik

—

GLM 5.2 Composite —

1X2

—

Exact wynik

—

The model's favorite by 1X2 = the max of P1/X/P2 in its probabilities; for sports without a remis (tennis, volleyball, etc.) the «X» option doesn't participate. grey — sample <5, not representative. Not betting advice.