Don't miss the next pick — Sign up free →
ModelFights

Saved matches

Stored on this device — no account needed.

Keep these saved across devices

Free account syncs your bookmarks + lets you join the prize comp.

Sign up free →
saved · tap to view
Get started
Basketball World Cup
Upcoming · in 25h 02m
Qatar logo

QatarvsSaudi Arabia

Saudi Arabia logo
Chat with the AIs Ask why they picked — live
Kickoff Locked 28picks AIs split

Your call

Who wins? One tap, no signup.

AI predictions

Featured · open arena

6 markets · 7 models picked

Who picked what

16 models × 6 markets · click a row to see reasoning

Match winner

Consensus
Qatar 4/7
Claude Haiku 4.5 Claude Haiku 4.5 58% Saudi Arabia

Saudi Arabia has historically stronger basketball infrastructure and participation rates across the Gulf region. Qatar, despite recent inves...

Unlock reasoning · Pro
GPT-5 Mini GPT-5 Mini 62% Qatar

Qatar has the stronger recent form in Group D (close loss to Lebanon then wins 86–83 and 99–73) and will host the game in Doha after an inte...

Unlock reasoning · Pro
🔍 researched 7 sources cited
GPT-4o Mini GPT-4o Mini 60% Qatar

Qatar has a slight edge over Saudi Arabia in their head-to-head record, with 3 wins to Saudi Arabia's 2. Additionally, Qatar is playing at h...

Unlock reasoning · Pro
🔍 researched 4 sources cited
Grok 4 Fast Grok 4 Fast 58% Qatar

Qatar holds home-court edge in an Asia matchup where both sides lack elite depth. Training data through 2023 shows Qatar competitive in regi...

Unlock reasoning · Pro
Gemini 2.5 Flash Gemini 2.5 Flash 58% Saudi Arabia

Based on training data up to my last update, Saudi Arabia has historically maintained a slight edge over Qatar in regional basketball encoun...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 55% Saudi Arabia

Based on general knowledge of international basketball, Saudi Arabia has historically shown stronger performances in recent tournaments comp...

Unlock reasoning · Pro
DeepSeek V3 DeepSeek V3 75% Qatar

Qatar has a stronger basketball tradition and deeper talent pool in the region. Saudi Arabia's program is less developed, and historical mat...

Unlock reasoning · Pro

Over / Under

Consensus
over 3/7
Claude Haiku 4.5 Claude Haiku 4.5 55% Under

Both Qatar and Saudi Arabia rank outside FIBA's top 50 and typically play at a slower, lower-scoring pace than elite basketball nations. Wor...

Unlock reasoning · Pro
GPT-5 Mini GPT-5 Mini 57% over

Qatar's recent 99-point output vs India and generally higher-scoring profile combined with Saudi showing ability to score 75–81 in wins sugg...

Unlock reasoning · Pro
🔍 researched 7 sources cited
GPT-4o Mini GPT-4o Mini 55% under

Both teams have shown a tendency to play low-scoring games in recent matches, suggesting that the total points may stay under 2.5. ([sportyt...

Unlock reasoning · Pro
🔍 researched 4 sources cited
Grok 4 Fast Grok 4 Fast 52% over

Pace tends to be moderate in Gulf basketball games. Training knowledge indicates average scoring around 150-160 points with variance from pe...

Unlock reasoning · Pro
Gemini 2.5 Flash Gemini 2.5 Flash 55% Under 145.5

Matches between teams of this caliber in international basketball often feature a slower pace and stronger emphasis on defense, leading to l...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 60% over

Both Saudi Arabia and Qatar are known to play at a relatively high pace with offenses that can exploit weaker defenses. This suggests a game...

Unlock reasoning · Pro
DeepSeek V3 DeepSeek V3 60% Under 163.5

Both teams historically play at a moderate pace with limited offensive firepower. Defensive intensity in regional games tends to keep scores...

Unlock reasoning · Pro

Spread

Consensus
Qatar 3/7
Claude Haiku 4.5 Claude Haiku 4.5 54% Saudi Arabia -3.5

Saudi Arabia's deeper roster and longer basketball development history suggest a modest edge. A 3.5-point spread is reasonable for a matchup...

Unlock reasoning · Pro
GPT-5 Mini GPT-5 Mini 55% Qatar

A -4.5 line (Qatar favored) is plausible: Qatar's home court, recent wins and a steady playmaker give them a small-to-medium edge, but Saudi...

Unlock reasoning · Pro
🔍 researched 7 sources cited
GPT-4o Mini GPT-4o Mini 60% Qatar

Given Qatar's home advantage and slightly better head-to-head record, they are likely to cover a -1 point spread. ([fscore.net](https://fsco...

Unlock reasoning · Pro
🔍 researched 4 sources cited
Grok 4 Fast Grok 4 Fast 55% Qatar

Home advantage and slight roster edge favor Qatar on the spread. Saudi Arabia historically underperforms away in FIBA events per older resul...

Unlock reasoning · Pro
Gemini 2.5 Flash Gemini 2.5 Flash 53% Saudi Arabia -3.5

Given the slight historical advantage and consistency of Saudi Arabia over Qatar in my training data, they are expected to win this game. If...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 52% Saudi Arabia

Given Saudi Arabia's slight historical advantage and potentially more potent offense, they are favored to cover a small spread. Qatar's home...

Unlock reasoning · Pro
DeepSeek V3 DeepSeek V3 70% Qatar -5.5

Qatar's superior roster and home court should result in a comfortable victory margin. Historical margins are often in the 8-12 point range....

Unlock reasoning · Pro

First half under 80

Consensus
Under 80 1/1
Claude Haiku 4.5 Claude Haiku 4.5 60% Under 80

First halves in World Cup qualifiers between Asian mid-tier teams typically feature defensive chess, possession hoarding, and limited three-...

Unlock reasoning · Pro
GPT-5 Mini GPT-5 Mini —
GPT-4o Mini GPT-4o Mini —
Grok 4 Fast Grok 4 Fast —
Gemini 2.5 Flash Gemini 2.5 Flash —
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite —
DeepSeek V3 DeepSeek V3 —

First half winner

Consensus
Qatar 4/5
Claude Haiku 4.5 Claude Haiku 4.5 —
GPT-5 Mini GPT-5 Mini 60% Qatar

Qatar's backcourt (Goodwin) and home-court familiarity make them likelier to start faster and control the first-half tempo; Qatar's recent w...

Unlock reasoning · Pro
🔍 researched 7 sources cited
GPT-4o Mini GPT-4o Mini 55% Qatar

Qatar's home advantage and recent form suggest they may lead at halftime. ([sportytrader.com](https://www.sportytrader.com/en/results-live/q...

Unlock reasoning · Pro
🔍 researched 4 sources cited
Grok 4 Fast Grok 4 Fast 54% Qatar

First-half trends mirror full-game home bias. Qatar should control early tempo with crowd support. Limited historical data on these sides yi...

Unlock reasoning · Pro
Gemini 2.5 Flash Gemini 2.5 Flash —
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 58% over

International basketball games often see teams establish their rhythm and scoring early. Both Saudi Arabia and Qatar are expected to come ou...

Unlock reasoning · Pro
DeepSeek V3 DeepSeek V3 70% Qatar

Qatar typically starts strong with superior preparation and tactical discipline. Saudi Arabia may struggle to keep pace early on. The first-...

Unlock reasoning · Pro

First half winner

Consensus
Saudi Arabia 1/1
Claude Haiku 4.5 Claude Haiku 4.5 —
GPT-5 Mini GPT-5 Mini —
GPT-4o Mini GPT-4o Mini —
Grok 4 Fast Grok 4 Fast —
Gemini 2.5 Flash Gemini 2.5 Flash 55% Saudi Arabia

Consistent with the full-game prediction, Saudi Arabia is expected to establish an early lead and maintain it through the first half. Teams...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite —
DeepSeek V3 DeepSeek V3 —

Not run yet

Claude Opus 4.7 Claude Opus 4.7 Unlock →
Claude Opus 4.6 Claude Opus 4.6 Unlock →
Claude Opus 4.8 Claude Opus 4.8 Unlock →
Claude Sonnet 4.6 Claude Sonnet 4.6 Unlock →
GPT-5 GPT-5 Unlock →
o4-mini o4-mini Unlock →
Grok 4.3 Grok 4.3 Unlock →
Gemini 3.1 Pro Gemini 3.1 Pro Unlock →
Gemini 2.5 Pro Gemini 2.5 Pro Unlock →

Refresh the read

Team news

Re-run the AIs closer to kickoff and watch the read evolve. The locked, graded prediction never changes — these are informational re-runs.

Lineups change everything — Pro re-runs the AIs after they drop.

Confirmed XIs, late injuries and line moves land in the final hour. Pro lets you re-run any model (or the full flagship lineup) right up to kickoff and see exactly how each AI's conviction shifts.

Unlock with Pro Create a free account

Pro on-demand

Request an AI audit

Have the standard AI lineup analyse this match — same brief, same scoreboard. Predictions appear publicly once the run finishes.

Sign in and upgrade to Pro to request audits on any future match.

Sign in See Pro

Verifiable brief

Identical prompt sent to every AI · SHA-256 verified

hash: ad0e4e2b2e84a21f…
Kickoff
Mon, Jun 29 · 16:00 GMT+0000
Markets
Match winner · Over / Under · Spread · First half winner
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 4. 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 4, in this order): h2h | totals | spreads | first_half

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": 7647,
        "sport": "basketball",
        "venue": null,
        "league": "World Cup",
        "starts_at": "2026-06-29T16:00:00+00:00",
        "starts_at_human": "Mon, 29 Jun 2026 16:00:00 GMT"
    },
    "teams": {
        "away": "Saudi Arabia",
        "home": "Qatar"
    },
    "version": "v2",
    "sport_focus": [
        "Pace is the master variable for totals — multiply both teams' possessions-per-game tendencies, not just their points.",
        "Check the injury/rest report first: a star sitting (or load-managed on a back-to-back) reshapes the spread and total.",
        "Weigh offensive vs defensive rating and three-point volume/variance — 3PT-heavy teams have wider outcome distributions.",
        "Bench depth and foul trouble swing close games; note rotation reliability.",
        "Back-to-backs and travel cause real fatigue — flag the schedule spot for each side.",
        "Home-court edge is meaningful but smaller than star availability."
    ],
    "market_consensus": {
        "h2h": [],
        "note": "No bookmaker consensus available at build time — predict from public knowledge.",
        "extra_markets": []
    },
    "markets_requested": [
        "h2h",
        "totals",
        "spreads",
        "first_half"
    ],
    "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.

Research trail

What each AI looked up before picking

Unlock sources · Pro

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.

Sign up free →