Dinamo TiranavsFC Astana
Free AI audit
Get a free AI pick on this match
No model has weighed in yet. Have DeepSeek V3 analyse this match — free, public, ~1 min.
Run a free AI audit — no account needed
One free DeepSeek pick per browser. Sign up after to save it, follow more matches, and unlock the full lineup.
Beat the AIs · Predict the score
Call the exact final score
Free account. Pick the exact final score, lock it before kickoff, beat the AI consensus across the WC and win a lifetime free plan.
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:
87e1ac23f5dab2d0…
- Kickoff
- Thu, Jul 9 · 19:00 GMT+0000
- Markets
- Match winner · Draw no bet · Over / Under 2.5 · Both teams to score · Spread -1 · Asian handicap · Half-time / Full-time · Correct score
- 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 8. 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 8, in this order): h2h | draw_no_bet | totals_2.5 | btts | spreads_-1 | asian_handicap | ht_ft | correct_score
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)
{
"version": "v2",
"event": {
"id": 10538,
"sport": "football",
"league": "UEFA Europa Conference League",
"starts_at": "2026-07-09T19:00:00+00:00",
"starts_at_human": "Thu, 09 Jul 2026 19:00:00 GMT",
"venue": "Elbasan Arena"
},
"teams": {
"home": "Dinamo Tirana",
"away": "FC Astana"
},
"market_consensus": {
"h2h": [],
"extra_markets": [],
"note": "No bookmaker consensus available at build time — predict from public knowledge."
},
"markets_requested": [
"h2h",
"draw_no_bet",
"totals_2.5",
"btts",
"spreads_-1",
"asian_handicap",
"ht_ft",
"correct_score"
],
"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`."
],
"sport_focus": [
"Weight CONFIRMED team news heavily: a missing first-choice striker, creator, or centre-back swings a match more than season-long form.",
"Compare attacking vs defensive quality directly — clean-sheet rate and goals-conceded trend often predict unders/BTTS better than the win line.",
"Set pieces decide tight games: note corner/free-kick threat and aerial mismatches.",
"Account for fixture congestion + likely rotation (midweek European or cup games before this one) and the home/away form split.",
"For outdoor venues, factor heavy rain or strong wind — both suppress goals and favour the under.",
"Tactical style matters: a high-press side vs a possession side, or two defensive setups, shapes the goals expectation."
],
"team_context": {
"home_form": {
"last": "W",
"record": "1W-0D-0L",
"scored": 2,
"conceded": 1,
"matches": 1
},
"away_form": {
"last": "WDLW",
"record": "2W-1D-1L",
"scored": 5,
"conceded": 4,
"matches": 4
},
"rest_days": {
"home": 16,
"away": 6
},
"note": "Reference data from our settled-results database. Verify + extend it with your own research; it is not a substitute for current team news."
}
}
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.
Results settle automatically once the final score lands. Picks are permanent — no hindsight edits.
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.