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
MLB Major League Baseball · Daikin Park
Upcoming · in 87h 58m
Houston Astros logo

Houston AstrosvsMiami Marlins

Miami Marlins 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

Ask the AIs

Who picked what

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

Match winner

Consensus
Houston Astros 4/7
Claude Opus 4.7 Claude Opus 4.7 Pro
Claude Opus 4.6 Claude Opus 4.6 Pro
Claude Opus 4.8 Claude Opus 4.8 Pro
Claude Sonnet 4.6 Claude Sonnet 4.6 Pro
Claude Haiku 4.5 Claude Haiku 4.5 58% Miami Marlins

Miami arrives in outstanding form (5-0 last 5 matches, +16 run differential) while Houston has stumbled (3-2 last 5 with neutral run differe...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 57% Miami Marlins

The Marlins arrive in good form (several strong recent starts from Max Meyer and top-end rotation pieces) while the Astros' best starter (Ar...

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

The Miami Marlins have demonstrated strong recent form, winning their last five matches with a total of 36 runs scored and 20 conceded. In c...

Unlock reasoning · Pro
🔍 researched 3 sources cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 62% Houston Astros

Astros have stronger overall roster and home advantage at Daikin Park against a weaker Marlins club. Training data through 2025-09 shows Hou...

Unlock reasoning · Pro
Gemini 3.1 Pro Gemini 3.1 Pro Pro
Gemini 2.5 Pro Gemini 2.5 Pro Pro
Gemini 2.5 Flash Gemini 2.5 Flash 55% Houston Astros

The Houston Astros typically leverage their home-field advantage and have a historically strong roster. While the Miami Marlins are on an im...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 65% Houston Astros

The Houston Astros are projected to have a stronger season than the Miami Marlins, who are expected to finish below .500. While starting pit...

Unlock reasoning · Pro
3 sources cited
DeepSeek V3 DeepSeek V3 58% Houston Astros

The Astros have a stronger overall roster and home-field advantage at Daikin Park. The Marlins have been hot recently but face a tougher opp...

Unlock reasoning · Pro

Over / Under

Consensus
over 5/7
Claude Opus 4.7 Claude Opus 4.7 Pro
Claude Opus 4.6 Claude Opus 4.6 Pro
Claude Opus 4.8 Claude Opus 4.8 Pro
Claude Sonnet 4.6 Claude Sonnet 4.6 Pro
Claude Haiku 4.5 Claude Haiku 4.5 62% Over 8.5

Miami's run-scoring form is exceptional (36 runs in 5 matches = 7.2 per game), and even Houston's modest output (31/5 = 6.2 per game) yields...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 56% over

Daikin Park (retractable roof, hitter-friendly dimensions) and Houston's tendency toward home runs increase total scoring risk, and both Mey...

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

Both teams have shown a tendency to score and concede a significant number of runs in recent games. The Marlins scored 36 runs and conceded...

Unlock reasoning · Pro
🔍 researched 3 sources cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 55% over

Ballpark and summer conditions at Daikin Park typically boost run scoring. Both teams show elevated offensive output in recent matches per t...

Unlock reasoning · Pro
Gemini 3.1 Pro Gemini 3.1 Pro Pro
Gemini 2.5 Pro Gemini 2.5 Pro Pro
Gemini 2.5 Flash Gemini 2.5 Flash 58% Over 9.5

Both teams have demonstrated recent offensive capability and been involved in high-scoring contests, with the Marlins scoring 36 runs in the...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 55% over

With both starting pitchers unannounced, and given the projected competitive nature of the Astros and the potential for the Marlins to strug...

Unlock reasoning · Pro
3 sources cited
DeepSeek V3 DeepSeek V3 55% over

Both teams have been scoring well recently, averaging over 6 runs per game. Daikin Park is a hitter-friendly park, and no dominant starting...

Unlock reasoning · Pro

Spread

Consensus
Miami Marlins 3/7
Claude Opus 4.7 Claude Opus 4.7 Pro
Claude Opus 4.6 Claude Opus 4.6 Pro
Claude Opus 4.8 Claude Opus 4.8 Pro
Claude Sonnet 4.6 Claude Sonnet 4.6 Pro
Claude Haiku 4.5 Claude Haiku 4.5 56% Miami Marlins +1.5

Miami's superior recent form (5-0 vs 3-2) and +16 run differential advantage support taking the away team plus runs. The +1.5 spread is a mo...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 62% Miami Marlins +1.5

Given my h2h lean toward the Marlins and the margin sensitivity of a 1.5-run spread, the safer expected-value play is taking Miami +1.5 (the...

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

Given the Marlins' superior recent form and the Astros' mixed performance, the Marlins are likely to cover the -1.5 spread, indicating a win...

Unlock reasoning · Pro
🔍 researched 3 sources cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 58% home_ -1.5

Houston's superior depth gives them a solid edge to win by multiple runs at home. Marlins struggle on the road against quality pitching staf...

Unlock reasoning · Pro
Gemini 3.1 Pro Gemini 3.1 Pro Pro
Gemini 2.5 Pro Gemini 2.5 Pro Pro
Gemini 2.5 Flash Gemini 2.5 Flash 52% Houston Astros -1.5

Picking the Houston Astros to cover the -1.5 spread aligns with their projected win at home. Strong home teams, particularly those with a re...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 52% Miami Marlins

While the Astros are favored, the Marlins' recent form, although against weaker competition, shows they can score runs. Given the uncertaint...

Unlock reasoning · Pro
3 sources cited
DeepSeek V3 DeepSeek V3 52% Miami Marlins

The Marlins have been in excellent form, winning their last five games. Even though the Astros are at home, a one-run spread gives the under...

Unlock reasoning · Pro

First 5 innings

Consensus
Houston Astros 4/7
Claude Opus 4.7 Claude Opus 4.7 Pro
Claude Opus 4.6 Claude Opus 4.6 Pro
Claude Opus 4.8 Claude Opus 4.8 Pro
Claude Sonnet 4.6 Claude Sonnet 4.6 Pro
Claude Haiku 4.5 Claude Haiku 4.5 54% Over 4.5

Early-inning scoring typically reflects lineup strength and starter command. Miami's hot form and +16 run differential suggest they are gene...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 50% Miami Marlins

First-five innings favor the team with the better starter and early offense; Max Meyer (or the Marlins' projected starter) has produced stro...

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

The Marlins' strong recent form suggests they are likely to take an early lead in the first five innings. Their consistent scoring in recent...

Unlock reasoning · Pro
🔍 researched 3 sources cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 60% Houston Astros

Astros typically jump on early leads at home with strong top-of-order production. Marlins bullpen and starters have shown vulnerability in f...

Unlock reasoning · Pro
Gemini 3.1 Pro Gemini 3.1 Pro Pro
Gemini 2.5 Pro Gemini 2.5 Pro Pro
Gemini 2.5 Flash Gemini 2.5 Flash 54% Houston Astros

The outcome of the first five innings is heavily influenced by the starting pitching matchup and early lineup performance. Without specific...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 62% Houston Astros

The Houston Astros are generally a stronger team and are playing at home. In the first five innings, they are more likely to establish an ea...

Unlock reasoning · Pro
3 sources cited
DeepSeek V3 DeepSeek V3 55% Houston Astros

The Astros have a strong bullpen and typically start well at home. The Marlins' recent run may not translate early against a solid Astros li...

Unlock reasoning · Pro

Model confidence

Conviction in pick · Match winner
Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite

Houston Astros

65
Grok 4 Fast

Grok 4 Fast

Houston Astros

62
GPT-4o Mini

GPT-4o Mini

Miami Marlins

60
Claude Haiku 4.5

Claude Haiku 4.5

Miami Marlins

58
DeepSeek V3

DeepSeek V3

Houston Astros

58
GPT-5 Mini

GPT-5 Mini

Miami Marlins

57
Gemini 2.5 Flash

Gemini 2.5 Flash

Houston Astros

55

Model track records

Lifetime

Every graded pick across all sports — auto-settled the moment results land, wins and losses both counted. Ranked by win rate.

GPT-5
GPT-5 145–91 · 61%
+67.5u
Claude Opus 4.8
Claude Opus 4.8 154–115 · 57%
-17.4u
GPT-4o Mini
GPT-4o Mini 1043–787 · 57%
-590.9u
GPT-5 Mini
GPT-5 Mini 678–576 · 54%
-356.7u
Gemini 3.1 Pro
Gemini 3.1 Pro 130–112 · 54%
+111.8u
o4-mini
o4-mini 90–78 · 54%
+69.7u
Claude Opus 4.6
Claude Opus 4.6 193–173 · 53%
-47.6u
Grok 4.3
Grok 4.3 132–124 · 52%
+93.6u
Claude Opus 4.7
Claude Opus 4.7 183–176 · 51%
-63.5u
Gemini 2.5 Flash
Gemini 2.5 Flash 1116–1095 · 50%
-909.7u
Grok 4 Fast
Grok 4 Fast 735–738 · 50%
-496.5u
DeepSeek V3
DeepSeek V3 1017–1031 · 50%
-722.4u
Claude Sonnet 4.6
Claude Sonnet 4.6 459–482 · 49%
-323.7u
Gemini 2.5 Flash-Lite
Gemini 2.5 Flash-Lite 864–915 · 49%
-713.8u
Claude Haiku 4.5
Claude Haiku 4.5 1004–1080 · 48%
-917.0u
Gemini 2.5 Pro
Gemini 2.5 Pro 151–179 · 46%
-73.8u

Units = net profit at flat 1-unit stakes. The full sortable board lives on the leaderboard.

Refresh the read

Early read

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: 85f309b7308b4751…
Kickoff
Tue, Jul 21 · 00:10 GMT+0000
Markets
Match winner · Over / Under · Spread · First 5 innings
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_five_innings

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": 13751,
        "sport": "baseball",
        "venue": "Daikin Park",
        "league": "Major League Baseball",
        "starts_at": "2026-07-21T00:10:00+00:00",
        "starts_at_human": "Tue, 21 Jul 2026 00:10:00 GMT"
    },
    "teams": {
        "away": "Miami Marlins",
        "home": "Houston Astros"
    },
    "version": "v2",
    "sport_focus": [
        "The starting-pitcher matchup is the single biggest factor — compare each starter's recent form, not just season ERA.",
        "Bullpen rest and usage over the last few days drives late-game and total outcomes.",
        "Ballpark factors matter: dimensions, altitude (e.g. Coors), and especially wind direction (out = more runs, in = fewer).",
        "Lineup handedness vs the opposing starter (L/R platoon splits) shifts the run expectation.",
        "Weather (wind, temperature, humidity) measurably affects carry and totals."
    ],
    "team_context": {
        "note": "Reference data from our settled-results database. Verify + extend it with your own research; it is not a substitute for current team news.",
        "away_form": {
            "last": "WWWWW",
            "record": "5W-0D-0L",
            "scored": 36,
            "matches": 5,
            "conceded": 20
        },
        "home_form": {
            "last": "LWLWW",
            "record": "3W-0D-2L",
            "scored": 31,
            "matches": 5,
            "conceded": 31
        },
        "rest_days": {
            "away": 12,
            "home": 12
        }
    },
    "market_consensus": {
        "h2h": [],
        "note": "No bookmaker consensus available at build time — predict from public knowledge.",
        "extra_markets": []
    },
    "markets_requested": [
        "h2h",
        "totals",
        "spreads",
        "first_five_innings"
    ],
    "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.

Share
Share X Reddit WhatsApp Telegram Facebook

Get the AI consensus before kickoff

Free. Pre-match alert per AI + see your picks graded as results land.

Sign up free →