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 22h 32m
Iran logo

IranvsSyria

Syria logo
Chat with the AIs Ask why they picked — live
Kickoff Locked 24picks

Your call

Who wins? One tap, no signup.

AI predictions

Featured · open arena

4 markets · 6 models picked

Who picked what

16 models × 4 markets · click a row to see reasoning

Match winner

Consensus
Iran 6/6
Claude Haiku 4.5 Claude Haiku 4.5 72% Iran

Iran is the stronger basketball program in West Asia with superior infrastructure, coaching depth, and player development pipelines. Syria h...

Unlock reasoning · Pro
GPT-5 Mini GPT-5 Mini 82% Iran

Iran have dominated recent head-to-heads (8–1) and enter the window with much higher offensive output (FIBA averages: Iran 80.0 PPG vs Syria...

Unlock reasoning · Pro
🔍 researched 4 sources cited
GPT-4o Mini GPT-4o Mini 85% Iran

Iran has a strong historical record against Syria, winning 7 out of 8 recent encounters. Their experience in international tournaments furth...

Unlock reasoning · Pro
🔍 researched 4 sources cited
Grok 4 Fast Grok 4 Fast 88% Iran

Iran has historically dominated Syria in FIBA Asia competitions and World Cup qualifiers with double-digit average margins. Syria lacks the...

Unlock reasoning · Pro
Gemini 2.5 Flash Gemini 2.5 Flash 85% Iran

Based on historical performance and general standing in Asian basketball, Iran is expected to be significantly stronger than Syria. Iran typ...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite —
DeepSeek V3 DeepSeek V3 75% Iran

Iran has historically been the stronger basketball team in Asia with deeper talent pool and experience. Syria lacks comparable depth and has...

Unlock reasoning · Pro

Over / Under

Consensus
under 2/6
Claude Haiku 4.5 Claude Haiku 4.5 65% Under

World Cup qualifiers and regional FIBA tournaments historically feature deliberate, defensive pacing—especially when one team (Iran) is stro...

Unlock reasoning · Pro
GPT-5 Mini GPT-5 Mini 65% under

Combined FIBA averages for the two teams are roughly 141.7 PPG (Iran ~80.0 + Syria ~61.7) which is below a 145.5 total; qualifiers' games in...

Unlock reasoning · Pro
🔍 researched 4 sources cited
GPT-4o Mini GPT-4o Mini 75% under

Both teams have shown tendencies towards lower-scoring games in recent encounters, with Iran's defense being particularly effective. ([fiba....

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

Iran typically plays at a moderate pace while Syria struggles defensively, inflating total points. Historical matches between these sides tr...

Unlock reasoning · Pro
Gemini 2.5 Flash Gemini 2.5 Flash 55% Under 155.5

As the stronger team, Iran will likely control the game's pace and deploy a robust defense against Syria. While Iran could score efficiently...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite —
DeepSeek V3 DeepSeek V3 60% under 160.5

Basketball games in Asia often feature slower pace compared to top leagues, and both Iran and Syria have modest offensive outputs. Recent ma...

Unlock reasoning · Pro

Spread

Consensus
Iran 3/6
Claude Haiku 4.5 Claude Haiku 4.5 68% Iran -8.5

Iran's talent and experience gap over Syria is substantial; expect a methodical 12–16 point victory. The spread of 8.5 is reasonable but sli...

Unlock reasoning · Pro
GPT-5 Mini GPT-5 Mini 66% Iran

Recent H2H margins and the team averages point to Iran being substantially stronger; multiple recent matchups were blowouts (e.g., 82–43 on...

Unlock reasoning · Pro
🔍 researched 4 sources cited
GPT-4o Mini GPT-4o Mini 80% Iran

Given Iran's superior record and home advantage, they are likely to cover a -1 point spread. ([fiba.basketball](https://www.fiba.basketball/...

Unlock reasoning · Pro
🔍 researched 4 sources cited
Grok 4 Fast Grok 4 Fast 82% Iran

Iran is expected to win by double digits given talent gap and home status. Syria rarely keeps contests close against top Asian sides. Traini...

Unlock reasoning · Pro
Gemini 2.5 Flash Gemini 2.5 Flash 60% Iran -20.5

Iran has consistently been a dominant force in Asian basketball, often securing large victories against weaker opponents like Syria. Their s...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite —
DeepSeek V3 DeepSeek V3 65% Iran -10.5

Iran's superior talent and home court should allow them to win by double digits. Syria's lack of consistent scoring threats makes covering a...

Unlock reasoning · Pro

First half winner

Consensus
Iran 5/6
Claude Haiku 4.5 Claude Haiku 4.5 70% Iran

Iran should establish early control and build a halftime lead of 5–8 points. Syria will likely start slowly against a stronger, home-court o...

Unlock reasoning · Pro
GPT-5 Mini GPT-5 Mini 70% Iran

Iran's offensive efficiency and head-to-head dominance usually translate into early leads; with Syria averaging ~61.7 PPG they have struggle...

Unlock reasoning · Pro
🔍 researched 4 sources cited
GPT-4o Mini GPT-4o Mini 70% Iran

Iran's strong start in previous matches suggests they will lead at halftime. ([fiba.basketball](https://www.fiba.basketball/en/events/fiba-a...

Unlock reasoning · Pro
🔍 researched 4 sources cited
Grok 4 Fast Grok 4 Fast 79% Iran

Iran establishes leads early due to superior starting units and preparation. Syria often starts slow in international play. Training data th...

Unlock reasoning · Pro
Gemini 2.5 Flash Gemini 2.5 Flash 78% Iran Win 1st Half

Iran's superior talent and strategic approach are expected to be evident from tip-off, allowing them to establish a comfortable lead and win...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite —
DeepSeek V3 DeepSeek V3 70% Iran

Iran often starts strong and establishes control early, leveraging their depth and experience. Syria may struggle to keep pace from the open...

Unlock reasoning · Pro

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: 83bbe125159bdbe8…
Kickoff
Mon, Jun 29 · 13:30 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": 7646,
        "sport": "basketball",
        "venue": null,
        "league": "World Cup",
        "starts_at": "2026-06-29T13:30:00+00:00",
        "starts_at_human": "Mon, 29 Jun 2026 13:30:00 GMT"
    },
    "teams": {
        "away": "Syria",
        "home": "Iran"
    },
    "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 →