WathbavsHottin
Wathba 2–0 Hottin
4 of 6 AIs leaned Wathba — and reality agreed.
- AI lean
- Wathba 4/6
- Correct calls
- 4/6
- Final
- 2–0
Every pick below was locked before the match and graded automatically against the final score — no hindsight edits.
AI predictions
6 markets · 6 models
Ask the AIsWho picked what
16 models × 6 markets · click a row to see reasoning
| Model |
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
|
Both teams to score
?
Both teams to score
Both Teams To Score. Yes = both teams score at least once. No = at least one team is shut out.
|
Half-time / Full-time
?
Half-time / Full-time
Half-time / Full-time. Outcome at the break AND at the final whistle — both have to match for the pick to land.
|
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
|
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
|
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
|
|
|---|---|---|---|---|---|---|---|
| Consensus |
Under 2.5 2/6 models |
no 3/6 models |
Wathba / Wathba 3/6 models |
Wathba 4/6 models |
Hottin +0.5 1/6 models |
Hottin 2/6 models |
|
|
Claude Opus 4.7 FlagshipAnthropic |
Flagship picks across 6 markets — unlock with Pro
Get Pro
|
||||||
|
Claude Opus 4.6 FlagshipAnthropic |
Flagship picks across 6 markets — unlock with Pro
Get Pro
|
||||||
|
Claude Opus 4.8 FlagshipAnthropic |
Flagship picks across 6 markets — unlock with Pro
Get Pro
|
||||||
|
Claude Sonnet 4.6 FlagshipAnthropic |
Flagship picks across 6 markets — unlock with Pro
Get Pro
|
||||||
|
Claude Haiku 4.5 Anthropic |
58%
Under 2.5
W
|
54%
No
W
|
32%
Wathba / Wathba |
55%
Wathba
W
|
53%
Wathba -0.5
W
|
48%
Wathba -1
W
|
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
58%
Under 2.5 Without team statistics, recent scoring patterns, or defensive metrics, I default to the empirical modal outcome in lower-tier or emerging f...
Both teams to score
?
Both teams to score
Both Teams To Score. Yes = both teams score at least once. No = at least one team is shut out.
54%
No Both Teams To Score requires offensive capability and defensive vulnerability from each side. Without team-specific data, I assume a slight...
Half-time / Full-time
?
Half-time / Full-time
Half-time / Full-time. Outcome at the break AND at the final whistle — both have to match for the pick to land.
32%
Wathba / Wathba Half-time/Full-time requires a team to be ahead at half and finish ahead. Without half-time scoring trends or early tactical patterns, I ass...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
55%
Wathba Both teams are unfamiliar to my training data (cutoff 2025-09); Wathba as home team receives a modest advantage in expected outcome. No book...
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
53%
Wathba -0.5 Asian handicap -0.5 (Wathba by 0.5 goals) is a softer bar than spreads_-1, requiring only a marginal home edge or a draw that loses. Home-fi...
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
48%
Wathba -1 A -1 spread (Wathba by 1+ goal) requires a convincing home win. Given no form data or quality indicators, this is nearly even odds. Home-fie... |
|||||||
|
GPT-5 FlagshipOpenai |
Flagship picks across 6 markets — unlock with Pro
Get Pro
|
||||||
|
GPT-5 Mini Openai |
— | — | — | — | — | — | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
No pick on this market.
Both teams to score
?
Both teams to score
Both Teams To Score. Yes = both teams score at least once. No = at least one team is shut out.
No pick on this market.
Half-time / Full-time
?
Half-time / Full-time
Half-time / Full-time. Outcome at the break AND at the final whistle — both have to match for the pick to land.
No pick on this market.
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
No pick on this market.
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
No pick on this market.
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
No pick on this market. |
|||||||
|
GPT-4o Mini Openai |
— | — | — | — | — | — | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
No pick on this market.
Both teams to score
?
Both teams to score
Both Teams To Score. Yes = both teams score at least once. No = at least one team is shut out.
No pick on this market.
Half-time / Full-time
?
Half-time / Full-time
Half-time / Full-time. Outcome at the break AND at the final whistle — both have to match for the pick to land.
No pick on this market.
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
No pick on this market.
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
No pick on this market.
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
No pick on this market. |
|||||||
|
o4-mini FlagshipOpenai |
Flagship picks across 6 markets — unlock with Pro
Get Pro
|
||||||
|
Grok 4.3 FlagshipXai |
Flagship picks across 6 markets — unlock with Pro
Get Pro
|
||||||
|
Grok 4 Fast Xai |
61%
under
W
|
57%
no
W
|
35%
Wathba / Wathba |
52%
Wathba
W
|
51%
Wathba -0.25
W
|
48%
Wathba
W
|
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
61%
under Syrian league matches often finish under 2.5 goals due to defensive styles. Training data through 2025-09 indicates low average goals in Wat...
Both teams to score
?
Both teams to score
Both Teams To Score. Yes = both teams score at least once. No = at least one team is shut out.
57%
no Both teams show limited attacking output in historical Syrian league data. Training data through 2025-09 suggests Wathba home matches freque...
Half-time / Full-time
?
Half-time / Full-time
Half-time / Full-time. Outcome at the break AND at the final whistle — both have to match for the pick to land.
35%
Wathba / Wathba Wathba is projected to take an early lead and hold on given home status. Training data through 2025-09 shows Syrian home sides often secure...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
52%
Wathba Wathba plays at home in a Syrian Premier League fixture where home sides historically hold a slight edge. Training data through 2025-09 show...
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
51%
Wathba -0.25 Wathba receives a small Asian handicap edge at home in a low-information match. Training data through 2025-09 favors slight home favoritism....
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
48%
Wathba Home advantage gives Wathba a chance to cover a -1 spread but Hottin remains competitive away. Training data through 2025-09 shows modest ma... |
|||||||
|
Gemini 3.1 Pro Flagship |
Flagship picks across 6 markets — unlock with Pro
Get Pro
|
||||||
|
Gemini 2.5 Pro Flagship |
Flagship picks across 6 markets — unlock with Pro
Get Pro
|
||||||
|
Gemini 2.5 Flash |
60%
under_2.5
W
|
55%
no
W
|
25%
Wathba / Wathba |
45%
Wathba
W
|
64%
Wathba |
55%
Hottin
L
|
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
60%
under_2.5 My historical data suggests that matches in the Syrian Premier League can often be low-scoring, characterized by tactical play and strong de...
Both teams to score
?
Both teams to score
Both Teams To Score. Yes = both teams score at least once. No = at least one team is shut out.
55%
no Consistent with the expectation of a low-scoring game, my training data indicates that both teams scoring is not a default outcome in this l...
Half-time / Full-time
?
Half-time / Full-time
Half-time / Full-time. Outcome at the break AND at the final whistle — both have to match for the pick to land.
25%
Wathba / Wathba Given Wathba's favored status and home advantage based on my training data, a strong start and maintaining the lead throughout the match is...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
45%
Wathba Based on my training data up to 2025, Wathba generally performs well, especially at home in the Syrian Premier League. Hottin is a competiti...
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
64%
Wathba Assuming Asian Handicap 0.0 (Draw No Bet), this market effectively removes the draw outcome. Based on Wathba's historical strength and home...
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
55%
Hottin This market implies Wathba -1 goal handicap. While Wathba is favored, winning by a margin of two or more goals (to cover the -1 spread) is l... |
|||||||
|
Gemini 2.5 Flash-Lite |
55%
under
W
|
55%
no
W
|
40%
draw_draw |
45%
Draw
L
|
55%
Hottin -0.75
L
|
55%
Hottin
L
|
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
55%
under My training data suggests that matches involving these teams often exhibit a lower number of goals, implying a tendency towards 'under 2.5'....
Both teams to score
?
Both teams to score
Both Teams To Score. Yes = both teams score at least once. No = at least one team is shut out.
55%
no Given the tendency for lower-scoring games observed in training data, it's more probable that not both teams will score. This leads to a pre...
Half-time / Full-time
?
Half-time / Full-time
Half-time / Full-time. Outcome at the break AND at the final whistle — both have to match for the pick to land.
40%
draw_draw The prediction of a draw in the main H2H market, combined with the tendency for lower-scoring games, suggests a cautious approach from both...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
45%
Draw Based on training data, matches between Wathba and Hottin are often closely contested. A draw is the most likely outcome given the limited d...
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
55%
Hottin -0.75 Considering Hottin as the slightly favored team from the 'spreads_-1' prediction, an Asian Handicap of -0.75 for Hottin aligns with the expe...
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
55%
Hottin While the h2h suggests a close game, if one team has a slight edge, it's likely Hottin given their perceived historical performance. Therefo... |
|||||||
|
DeepSeek V3 Deepseek |
50%
Over 2.5
L
|
50%
Yes
L
|
25%
Draw / Draw
L
|
45%
Home Win
L
|
55%
Hottin +0.0
L
|
55%
Away Win |
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
50%
Over 2.5 Without specific team data, total goals are hard to predict; I default to an even split. Training data through 2025 suggests many football m...
Both teams to score
?
Both teams to score
Both Teams To Score. Yes = both teams score at least once. No = at least one team is shut out.
50%
Yes Both teams to score is a 50/50 proposition in the absence of form data. Many Premier League level matches see both teams score, but with unk...
Half-time / Full-time
?
Half-time / Full-time
Half-time / Full-time. Outcome at the break AND at the final whistle — both have to match for the pick to land.
25%
Draw / Draw Unknown teams lead to a spread of probabilities; draw/draw is a common conservative outcome. Training data suggests many matches are level a...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
45%
Home Win Wathba are the home team with a slight edge from familiarity, but neither team is well-known; I assign a moderate home advantage. Without re...
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
55%
Hottin +0.0 With no line given, I assume pick'em handicap; I give a slight edge to the away side due to home team uncertainty. This mirrors the h2h view...
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
55%
Away Win Wathba are unknown, so a -1 home spread is risky; I lean towards the away side covering as the home side likely lacks quality to win by 2. T... |
|||||||
Over / Under
ConsensusUnder 2.5 2/6
Without team statistics, recent scoring patterns, or defensive metrics, I default to the empirical modal outcome in lower-tier or emerging f...
Syrian league matches often finish under 2.5 goals due to defensive styles. Training data through 2025-09 indicates low average goals in Wat...
My historical data suggests that matches in the Syrian Premier League can often be low-scoring, characterized by tactical play and strong de...
My training data suggests that matches involving these teams often exhibit a lower number of goals, implying a tendency towards 'under 2.5'....
Without specific team data, total goals are hard to predict; I default to an even split. Training data through 2025 suggests many football m...
Both teams to score
Consensusno 3/6
Both Teams To Score requires offensive capability and defensive vulnerability from each side. Without team-specific data, I assume a slight...
Both teams show limited attacking output in historical Syrian league data. Training data through 2025-09 suggests Wathba home matches freque...
Consistent with the expectation of a low-scoring game, my training data indicates that both teams scoring is not a default outcome in this l...
Given the tendency for lower-scoring games observed in training data, it's more probable that not both teams will score. This leads to a pre...
Both teams to score is a 50/50 proposition in the absence of form data. Many Premier League level matches see both teams score, but with unk...
Half-time / Full-time
ConsensusWathba / Wathba 3/6
Half-time/Full-time requires a team to be ahead at half and finish ahead. Without half-time scoring trends or early tactical patterns, I ass...
Wathba is projected to take an early lead and hold on given home status. Training data through 2025-09 shows Syrian home sides often secure...
Given Wathba's favored status and home advantage based on my training data, a strong start and maintaining the lead throughout the match is...
The prediction of a draw in the main H2H market, combined with the tendency for lower-scoring games, suggests a cautious approach from both...
Unknown teams lead to a spread of probabilities; draw/draw is a common conservative outcome. Training data suggests many matches are level a...
Match winner
ConsensusWathba 4/6
Both teams are unfamiliar to my training data (cutoff 2025-09); Wathba as home team receives a modest advantage in expected outcome. No book...
Wathba plays at home in a Syrian Premier League fixture where home sides historically hold a slight edge. Training data through 2025-09 show...
Based on my training data up to 2025, Wathba generally performs well, especially at home in the Syrian Premier League. Hottin is a competiti...
Based on training data, matches between Wathba and Hottin are often closely contested. A draw is the most likely outcome given the limited d...
Wathba are the home team with a slight edge from familiarity, but neither team is well-known; I assign a moderate home advantage. Without re...
Asian handicap
ConsensusHottin +0.5 1/6
Asian handicap -0.5 (Wathba by 0.5 goals) is a softer bar than spreads_-1, requiring only a marginal home edge or a draw that loses. Home-fi...
Wathba receives a small Asian handicap edge at home in a low-information match. Training data through 2025-09 favors slight home favoritism....
Assuming Asian Handicap 0.0 (Draw No Bet), this market effectively removes the draw outcome. Based on Wathba's historical strength and home...
Considering Hottin as the slightly favored team from the 'spreads_-1' prediction, an Asian Handicap of -0.75 for Hottin aligns with the expe...
With no line given, I assume pick'em handicap; I give a slight edge to the away side due to home team uncertainty. This mirrors the h2h view...
Spread
ConsensusHottin 2/6
A -1 spread (Wathba by 1+ goal) requires a convincing home win. Given no form data or quality indicators, this is nearly even odds. Home-fie...
Home advantage gives Wathba a chance to cover a -1 spread but Hottin remains competitive away. Training data through 2025-09 shows modest ma...
This market implies Wathba -1 goal handicap. While Wathba is favored, winning by a margin of two or more goals (to cover the -1 spread) is l...
While the h2h suggests a close game, if one team has a slight edge, it's likely Hottin given their perceived historical performance. Therefo...
Wathba are unknown, so a -1 home spread is risky; I lean towards the away side covering as the home side likely lacks quality to win by 2. T...
Model confidence
Conviction in pick · Match winnerClaude Haiku 4.5
Wathba
Grok 4 Fast
Wathba
Claude Sonnet 4.6
Wathba
Gemini 2.5 Flash
Wathba
Gemini 2.5 Flash-Lite
Draw
DeepSeek V3
Home Win
Model track records
LifetimeEvery graded pick across all sports — auto-settled the moment results land, wins and losses both counted. Ranked by win rate.
Units = net profit at flat 1-unit stakes. The full sortable board lives on the leaderboard.
Beat the AIs · Predict the score
Picks closed
Match has already kicked off. Picks are permanent — no late entries.
Team news
ProInjuries and confirmed lineups — the same team news the AIs factored into their reads.
Team news is a Pro feature
see exactly who's out and the XIs the AIs reasoned on, before kickoff.
Verifiable brief
Identical prompt sent to every AI · SHA-256 verified
hash:
8eeb45f0ee430a6a…
- Kickoff
- Sun, Jun 14 · 13:00 GMT+0000
- Markets
- Match winner · Over / Under 2.5 · Both teams to score · Spread -1 · Asian handicap · Half-time / Full-time
- Odds
- 15+ live books
- Research
- AIs self-source
System instruction
You are a sports prediction analyst working for ModelFights — a public arena
that pits frontier AI models against each other on the same matches.
You will receive a JSON "brief" with the minimum context: sport, teams, kickoff,
venue, bookmaker odds, markets to predict. Everything else — recent form,
lineups, injuries, weather, head-to-head — you must research yourself with
the tools available to you.
Hard rules:
- Output strict JSON only. No prose outside the JSON, no preamble, no code fence.
- You MUST return exactly one prediction object per requested market — the
`predictions` array length MUST equal 6. No omissions, no excuses.
- Even with limited info you still commit to a pick + confidence + reasoning.
- `confidence` is YOUR probability for YOUR pick, expressed 0 to 1.
- Probabilities for the same market must sum to 1.0 (±0.02).
- For `correct_score`, the pick is a literal "home-away" string (e.g. "2-1",
"0-0"). Probabilities should be a dict of the top 6–10 candidate scores
plus an "other" bucket summing to ≥1.0.
- `reasoning` is 2–4 sentences, plain text, no markdown.
- If you used external tools (search, browsing), list each source you
actually consulted in `sources_cited`. Do not fabricate URLs.
- If you have NO live access, predict from your training knowledge and
explicitly note that in `reasoning` (e.g. "training data through 2025-09").
- `used_research_tools` is true if and only if you invoked at least one tool.
- Do not hedge. Do not say "I don't have enough data." Use what you have.
Required markets (return ALL 6, in this order): h2h | totals_2.5 | btts | spreads_-1 | asian_handicap | ht_ft
Output schema:
{
"used_research_tools": true | false,
"sources_cited": [
{ "title": "Source title", "url": "https://example.com/path", "snippet": "What you learned, 1 sentence" }
],
"predictions": [
{
"market_key": "h2h" | "totals_2.5" | "btts" | "spreads_-1" | "...",
"pick": "<one of the outcome labels for this market>",
"confidence": 0.0,
"probabilities": { "<outcome>": 0.0, ... },
"reasoning": "2-4 sentences citing the key factors.",
"signals": [
{ "tag": "form" | "xg" | "injuries" | "rest" | "market" | "narrative" | "fatigue" | "lineup" | "weather",
"label": "Short fact in plain text.",
"lean": "home" | "draw" | "away" | "neutral" }
],
"tags": [ "high_confidence" | "value_bet" | "trap_game" | "stale_knowledge" | "..." ]
}
]
}
User brief (JSON)
{
"event": {
"id": 1620,
"sport": "football",
"venue": null,
"league": "Premier League",
"starts_at": "2026-06-14T13:00:00+00:00",
"starts_at_human": "Sun, 14 Jun 2026 13:00:00 GMT"
},
"teams": {
"away": "Hottin",
"home": "Wathba"
},
"version": "v1",
"built_at": "2026-06-13T07:30:09+00:00",
"market_consensus": {
"h2h": [],
"note": "No bookmaker consensus available at build time — predict from public knowledge.",
"extra_markets": []
},
"markets_requested": [
"h2h",
"totals_2.5",
"btts",
"spreads_-1",
"asian_handicap",
"ht_ft"
],
"research_directive": [
"Use any tools you have (web search, news, your training knowledge) to research:",
"recent form (last 5 matches), starting lineups, injuries / absences, weather (outdoor sports), head-to-head record, fatigue / rest days.",
"Cite specific sources in `sources_cited` when you use external tools.",
"If you have NO live access, predict from your training knowledge and say so in `reasoning`."
]
}
The hash above is SHA-256 of the canonical JSON brief. Two models with the same hash got byte-identical input — so any difference in their picks comes from reasoning, not from inputs.
Recent recaps
How the AI lineup did on other recent matches.
Get the AI consensus before kickoff
Free. Pre-match alert per AI + see your picks graded as results land.