JSKvsSimba
JSK 1–0 Simba
5 of 6 AIs leaned JSK — and reality agreed.
- AI lean
- JSK 5/6
- Correct calls
- 5/6
- Final
- 1–0
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 |
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
|
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.
|
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).
|
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.
|
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
|
|
|---|---|---|---|---|---|---|---|
| Consensus |
JSK 5/6 models |
Under 2.5 3/6 models |
yes 2/6 models |
Simba 2/6 models |
Draw / JSK 2/6 models |
JSK -0.5 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 |
62%
JSK
W
|
58%
Under 2.5
W
|
55%
No
W
|
52%
JSK |
45%
JSK / JSK |
60%
JSK -0.5
W
|
|
|
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
62%
JSK JSK is listed as home team in Ligue 1, which provides a typical 3–5% home-ground advantage. Without access to current form, injuries, or hea...
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
58%
Under 2.5 Ligue 1 mid-season and cross-regional matchups often feature tight, defensive setups, especially if teams are fatigued or unfamiliar with ea...
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 Both teams scoring requires sustained attacking play from both sides and generally weaker defenses. In the absence of current form and team...
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).
52%
JSK A -1 spread (JSK to win by at least 2) is a higher barrier than simple home advantage. While JSK has home-ground benefit, winning by 2+ goal...
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.
45%
JSK / JSK Half-time/full-time results are highly dependent on early momentum and team intensity. JSK/JSK (JSK leading and winning) is the most probabl...
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
60%
JSK -0.5 Asian handicap at -0.5 (JSK to win or draw) is less demanding than -1 and aligns more naturally with home advantage. This pick reflects conf... |
|||||||
GPT-5 FlagshipOpenai |
Flagship picks across 6 markets — unlock with Pro
Get Pro
|
||||||
|
GPT-5 Mini Openai |
— | — | — | — | — | — | |
|
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.
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.
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.
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.
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. |
|||||||
|
GPT-4o Mini Openai |
— | — | — | — | — | — | |
|
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.
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.
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.
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.
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. |
|||||||
|
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 |
52%
JSK
W
|
55%
over
L
|
53%
yes
L
|
48%
home_ -1 |
30%
home_home |
52%
home_ -0.5 |
|
|
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
52%
JSK JSK listed as home side in this fixture. Training data through 2025-09 indicates home sides win roughly half of similar low-info African clu...
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
55%
over Limited data on both sides suggests open matches; training knowledge points to slight lean toward over 2.5 goals in comparable fixtures.
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.
53%
yes Both teams typically concede in their domestic games per historical patterns. Training cutoff leaves no updated lineups or form.
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%
home_ -1 Home advantage gives JSK a narrow edge on -1 spread but away side retains value. All inputs from pre-2026 knowledge only.
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.
30%
home_home Home win to home win remains most probable double result on historical averages. No live data available beyond 2025 training cutoff.
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
52%
home_ -0.5 Standard home favorite status in absence of other data. Prediction drawn solely from training knowledge through 2025. |
|||||||
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 |
38%
JSK
W
|
58%
under
W
|
55%
no
W
|
45%
Simba
L
|
28%
Draw / JSK |
55%
JSK |
|
|
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
38%
JSK Based on my training data through early 2024, JS Kabylie generally holds a slightly stronger historical standing in African club competition...
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
58%
under Matches between competitive African clubs, especially without clear dominant form, often tend to be cagey and low-scoring affairs. My traini...
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 Aligning with the expectation of a low-scoring, tight match, it's more probable that at least one team will fail to score. Defensive solidit...
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).
45%
Simba Considering a tight contest and the strong historical competitive level of both teams from my training data, it is unlikely JSK will win by...
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.
28%
Draw / JSK Many competitive football matches, especially in continental competitions, often see a cautious first half ending in a draw. Based on my gen...
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
55%
JSK Assuming an Asian Handicap 0.0 (Draw No Bet) due to no specific line being provided, this prediction aligns with the slight historical compe... |
|||||||
|
Gemini 2.5 Flash-Lite |
45%
Simba
L
|
55%
over
L
|
58%
yes
L
|
48%
Simba
L
|
38%
Draw / Simba
L
|
52%
Simba |
|
|
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
45%
Simba Based on training data, Simba has historically performed better against JSK in head-to-head encounters. Simba is also generally the stronger...
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
55%
over Both JSK and Simba have demonstrated a tendency to score and concede goals in their recent matches. This suggests a higher likelihood of the...
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.
58%
yes The attacking styles of both JSK and Simba, coupled with their defensive vulnerabilities, indicate that both teams are likely to find the ba...
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%
Simba While Simba is favored, JSK is expected to put up a fight at home. Simba might win, but covering a -1 handicap is less certain due to JSK's...
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.
38%
Draw / Simba Simba is expected to win, but JSK is capable of holding them off for the first half. A draw at halftime followed by a Simba victory in the s...
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
52%
Simba Simba is the stronger team and is expected to win. An Asian Handicap of 0 for Simba offers good value as it covers a win and pushes on a dra... |
|||||||
DeepSeek V3 Deepseek |
45%
JSK
W
|
50%
Under 2.5
W
|
55%
Both teams to score - Yes
L
|
30%
JSK -1 |
30%
JSK / JSK |
55%
Simba +0.5
L
|
|
|
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
45%
JSK JSK typically have strong home support in Ligue 1, while Simba are less familiar in this league. However, current form data is unavailable d...
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
50%
Under 2.5 With no recent form data, league averages suggest Ligue 1 matches often hover around 2.5 goals. Given uncertainty, both outcomes are equally...
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%
Both teams to score - Yes Generic league statistics show a slight tendency for BTTS in domestic competitions, but specific team data is absent. Slight lean towards Ye...
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).
30%
JSK -1 The -1 handicap requires JSK to win by two clear goals, which is unlikely without strong form evidence. Home win by a narrow margin is more...
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.
30%
JSK / JSK Home win at halftime and fulltime is the most likely single outcome from the limited conditions. However, low confidence due to lack of spec...
Asian handicap
?
Asian handicap
Asian Handicap. Like a spread, but quarter-lines split the stake — you can half-win or half-push.
55%
Simba +0.5 Without clear form, Simba at +0.5 offers value as underdog. JSK's home advantage is offset by uncertainty, making Simba covering a slight fa... |
|||||||
Match winner
ConsensusJSK 5/6
Claude Haiku 4.5
62%
JSK
W
JSK is listed as home team in Ligue 1, which provides a typical 3–5% home-ground advantage. Without access to current form, injuries, or hea...
GPT-5 Mini
—
GPT-4o Mini
—
Grok 4 Fast
52%
JSK
W
JSK listed as home side in this fixture. Training data through 2025-09 indicates home sides win roughly half of similar low-info African clu...
Gemini 2.5 Flash
38%
JSK
W
Based on my training data through early 2024, JS Kabylie generally holds a slightly stronger historical standing in African club competition...
Gemini 2.5 Flash-Lite
45%
Simba
L
Based on training data, Simba has historically performed better against JSK in head-to-head encounters. Simba is also generally the stronger...
DeepSeek V3
45%
JSK
W
JSK typically have strong home support in Ligue 1, while Simba are less familiar in this league. However, current form data is unavailable d...
Over / Under
ConsensusUnder 2.5 3/6
Claude Haiku 4.5
58%
Under 2.5
W
Ligue 1 mid-season and cross-regional matchups often feature tight, defensive setups, especially if teams are fatigued or unfamiliar with ea...
GPT-5 Mini
—
GPT-4o Mini
—
Grok 4 Fast
55%
over
L
Limited data on both sides suggests open matches; training knowledge points to slight lean toward over 2.5 goals in comparable fixtures.
Gemini 2.5 Flash
58%
under
W
Matches between competitive African clubs, especially without clear dominant form, often tend to be cagey and low-scoring affairs. My traini...
Gemini 2.5 Flash-Lite
55%
over
L
Both JSK and Simba have demonstrated a tendency to score and concede goals in their recent matches. This suggests a higher likelihood of the...
DeepSeek V3
50%
Under 2.5
W
With no recent form data, league averages suggest Ligue 1 matches often hover around 2.5 goals. Given uncertainty, both outcomes are equally...
Both teams to score
Consensusyes 2/6
Claude Haiku 4.5
55%
No
W
Both teams scoring requires sustained attacking play from both sides and generally weaker defenses. In the absence of current form and team...
GPT-5 Mini
—
GPT-4o Mini
—
Grok 4 Fast
53%
yes
L
Both teams typically concede in their domestic games per historical patterns. Training cutoff leaves no updated lineups or form.
Gemini 2.5 Flash
55%
no
W
Aligning with the expectation of a low-scoring, tight match, it's more probable that at least one team will fail to score. Defensive solidit...
Gemini 2.5 Flash-Lite
58%
yes
L
The attacking styles of both JSK and Simba, coupled with their defensive vulnerabilities, indicate that both teams are likely to find the ba...
DeepSeek V3
55%
Both teams to score - Yes
L
Generic league statistics show a slight tendency for BTTS in domestic competitions, but specific team data is absent. Slight lean towards Ye...
Spread
ConsensusSimba 2/6
Claude Haiku 4.5
52%
JSK
A -1 spread (JSK to win by at least 2) is a higher barrier than simple home advantage. While JSK has home-ground benefit, winning by 2+ goal...
GPT-5 Mini
—
GPT-4o Mini
—
Grok 4 Fast
48%
home_ -1
Home advantage gives JSK a narrow edge on -1 spread but away side retains value. All inputs from pre-2026 knowledge only.
Gemini 2.5 Flash
45%
Simba
L
Considering a tight contest and the strong historical competitive level of both teams from my training data, it is unlikely JSK will win by...
Gemini 2.5 Flash-Lite
48%
Simba
L
While Simba is favored, JSK is expected to put up a fight at home. Simba might win, but covering a -1 handicap is less certain due to JSK's...
DeepSeek V3
30%
JSK -1
The -1 handicap requires JSK to win by two clear goals, which is unlikely without strong form evidence. Home win by a narrow margin is more...
Half-time / Full-time
ConsensusDraw / JSK 2/6
Claude Haiku 4.5
45%
JSK / JSK
Half-time/full-time results are highly dependent on early momentum and team intensity. JSK/JSK (JSK leading and winning) is the most probabl...
GPT-5 Mini
—
GPT-4o Mini
—
Grok 4 Fast
30%
home_home
Home win to home win remains most probable double result on historical averages. No live data available beyond 2025 training cutoff.
Gemini 2.5 Flash
28%
Draw / JSK
Many competitive football matches, especially in continental competitions, often see a cautious first half ending in a draw. Based on my gen...
Gemini 2.5 Flash-Lite
38%
Draw / Simba
L
Simba is expected to win, but JSK is capable of holding them off for the first half. A draw at halftime followed by a Simba victory in the s...
DeepSeek V3
30%
JSK / JSK
Home win at halftime and fulltime is the most likely single outcome from the limited conditions. However, low confidence due to lack of spec...
Asian handicap
ConsensusJSK -0.5 2/6
Claude Haiku 4.5
60%
JSK -0.5
W
Asian handicap at -0.5 (JSK to win or draw) is less demanding than -1 and aligns more naturally with home advantage. This pick reflects conf...
GPT-5 Mini
—
GPT-4o Mini
—
Grok 4 Fast
52%
home_ -0.5
Standard home favorite status in absence of other data. Prediction drawn solely from training knowledge through 2025.
Gemini 2.5 Flash
55%
JSK
Assuming an Asian Handicap 0.0 (Draw No Bet) due to no specific line being provided, this prediction aligns with the slight historical compe...
Gemini 2.5 Flash-Lite
52%
Simba
Simba is the stronger team and is expected to win. An Asian Handicap of 0 for Simba offers good value as it covers a win and pushes on a dra...
DeepSeek V3
55%
Simba +0.5
L
Without clear form, Simba at +0.5 offers value as underdog. JSK's home advantage is offset by uncertainty, making Simba covering a slight fa...
Model confidence
Conviction in pick · Match winner
Claude Haiku 4.5
JSK
Grok 4 Fast
JSK
Claude Sonnet 4.6
JSK
Gemini 2.5 Flash-Lite
Simba
DeepSeek V3
JSK
Gemini 2.5 Flash
JSK
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:
e9239f83f5f031d5…
- Kickoff
- Sun, Jun 14 · 14:00 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": 1609,
"sport": "football",
"venue": null,
"league": "Ligue 1",
"starts_at": "2026-06-14T13:00:00+00:00",
"starts_at_human": "Sun, 14 Jun 2026 13:00:00 GMT"
},
"teams": {
"away": "Simba",
"home": "JSK"
},
"version": "v1",
"built_at": "2026-06-13T07:32:50+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.