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
Upcoming · in 84h 02m
Chicago Cubs logo

Chicago CubsvsSt.Louis Cardinals

St.Louis Cardinals logo
Chat with the AIs Ask why they picked — live
Kickoff Locked 28picks

Your call

Who wins? One tap, no signup.

AI predictions

5 markets · 7 models picked

Consensus split

How the lineup voted · Match winner

7 picks
  • Chicago Cubs 100% 7/7

Model confidence

Each model's confidence in its pick (%)

Who picked what

16 models × 5 markets · click a row to see reasoning

First 5 innings

Consensus
Chicago Cubs 6/6
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 61% Chicago Cubs

Early-game performance is typically determined by starting pitcher quality and lineup handedness matchup, both unknown here. However, Cubs'...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini —
GPT-4o Mini GPT-4o Mini 60% Chicago Cubs

The Cubs' strong recent performance and home advantage suggest they will lead after the first five innings. The Cardinals' recent struggles...

Unlock reasoning · Pro
🔍 researched 1 source cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 52% Chicago Cubs

Early-game edge tilts to Cubs given overall form differential and home start. Starting pitching form is unknown but home lineup advantage us...

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% Chicago Cubs

The first five innings outcome is heavily influenced by the starting pitchers and early offensive execution. Without specific pitcher inform...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 54% Chicago Cubs

The Cubs' superior recent form and home-field advantage are likely to carry over into the early innings. Their tendency to start strong in r...

Unlock reasoning · Pro
3 sources cited
DeepSeek V3 DeepSeek V3 60% Chicago Cubs

Cubs' offense has been hot recently, likely scoring early. Cardinals have struggled early in games (1-4). Starting pitchers unknown but Cubs...

Unlock reasoning · Pro

Match winner

Consensus
Chicago Cubs 7/7
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 68% Chicago Cubs

The Cubs enter with strong recent form (4W-1L over last 5) and a +5 run differential, while the Cardinals are in free-fall at 1W-4L with a -...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 58% Chicago Cubs

CBS's matchup lists Andre Pallante (Cardinals) vs. Javier Assad (Cubs); Pallante has been pitching well recently but Assad has delivered qua...

Unlock reasoning · Pro
🔍 researched 6 sources cited
GPT-4o Mini GPT-4o Mini 65% Chicago Cubs

The Chicago Cubs have been in strong form recently, winning four of their last five games, while the St. Louis Cardinals have struggled, los...

Unlock reasoning · Pro
🔍 researched 1 source cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 56% Chicago Cubs

Cubs enter with superior recent form (WWWLW) versus Cardinals (WLLLL) per provided context. Home-field edge at Wrigley and 3 rest days still...

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 65% Chicago Cubs

Based on the provided team form, the Chicago Cubs are performing significantly better (4W-1L) compared to the St.Louis Cardinals (1W-4L). Th...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 55% Chicago Cubs

The Chicago Cubs have shown significantly better recent form (4-1 in last 5) compared to the St. Louis Cardinals (1-4 in last 5). While star...

Unlock reasoning · Pro
3 sources cited
DeepSeek V3 DeepSeek V3 65% Chicago Cubs

Cubs have strong recent form (4-1 last 5) compared to Cardinals (1-4) and home field advantage at Wrigley. Rest advantage for Cards (5 days...

Unlock reasoning · Pro

Over / Under

Consensus
over 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% Over

Cubs have averaged 4.2 runs/game and Cardinals 2.0 runs/game over the last 5 matches, totaling 6.2 combined. However, Cubs' offensive streng...

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

Pallante's last month includes multiple starts with two or fewer runs allowed and Assad has been a streaky but often contact-oriented pitche...

Unlock reasoning · Pro
🔍 researched 6 sources cited
GPT-4o Mini GPT-4o Mini 60% over

Both teams have shown inconsistent pitching performances recently, leading to higher-scoring games. The Cubs' offense has been potent, and t...

Unlock reasoning · Pro
🔍 researched 1 source cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 53% over

Cardinals have allowed 23 runs in last 5 games while Cubs offense is clicking at 21 runs scored. Ballpark and July weather typically inflate...

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% Under 8.5

Analyzing recent game averages from the brief, the Cardinals' offense has been particularly anemic (2 runs/game) while their pitching has co...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 52% over

While neither team's recent scoring has been exceptional, the historical matchup between these two teams often sees a moderate number of run...

Unlock reasoning · Pro
3 sources cited
DeepSeek V3 DeepSeek V3 55% over 8.5

Both bullpens have been inconsistent recently. July games at Wrigley often see higher scoring due to warm weather. Given average starters no...

Unlock reasoning · Pro

Spread

Consensus
Chicago Cubs -1.5 2/7
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 57% Chicago Cubs -1.5

Cubs' dominant recent form (4W-1L, +5 run diff) and Cardinals' collapse (1W-4L, -13 run diff) support a 1–2 run margin favouring the home si...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 55% St.Louis Cardinals +1.5

Given Pallante's recent ability to keep games close and the Cubs' occasional offensive inconsistency, the +1.5 spread for the Cardinals prov...

Unlock reasoning · Pro
🔍 researched 6 sources cited
GPT-4o Mini GPT-4o Mini 55% Chicago Cubs

The Cubs' recent form and home advantage suggest they are likely to win by at least one run. However, the Cardinals' potential for an upset...

Unlock reasoning · Pro
🔍 researched 1 source cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 54% Chicago Cubs

Cubs strong form and home status give them the edge to cover a standard run line. Cardinals poor recent results limit their ability to stay...

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 60% Chicago Cubs -1.5

Given the significant disparity in recent team form and the strong H2H pick for the Cubs, they are expected to win this game by a comfortabl...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 53% St.Louis Cardinals

Given the Cubs' better recent form and home advantage, they are favored to win. However, the Cardinals' recent struggles might lead to them...

Unlock reasoning · Pro
3 sources cited
DeepSeek V3 DeepSeek V3 45% CHC -1.5

Cubs are favorites with better form, but covering -1.5 is challenging. Cardinals may bounce back with extra rest. Expect a close game, makin...

Unlock reasoning · Pro

First five innings 4.5

Consensus
under 1/1
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 —
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 60% under

Both projected starters (Pallante and Assad) have recent starts where they handled early innings efficiently; Pallante specifically has mult...

Unlock reasoning · Pro
🔍 researched 6 sources cited
GPT-4o Mini GPT-4o Mini —
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast —
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 —
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite —
DeepSeek V3 DeepSeek V3 —

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 96–72 · 57%
-14.6u
Claude Opus 4.8
Claude Opus 4.8 101–89 · 53%
-31.9u
GPT-4o Mini
GPT-4o Mini 552–533 · 51%
-384.4u
o4-mini
o4-mini 53–52 · 50%
-17.6u
GPT-5 Mini
GPT-5 Mini 402–405 · 50%
-207.1u
Claude Opus 4.7
Claude Opus 4.7 142–144 · 50%
-45.3u
Claude Opus 4.6
Claude Opus 4.6 142–147 · 49%
-42.1u
Gemini 2.5 Flash
Gemini 2.5 Flash 692–758 · 48%
-594.0u
DeepSeek V3
DeepSeek V3 685–757 · 48%
-457.4u
Claude Sonnet 4.6
Claude Sonnet 4.6 407–456 · 47%
-316.4u
Grok 4 Fast
Grok 4 Fast 522–591 · 47%
-364.3u
Grok 4.3
Grok 4.3 84–96 · 47%
-35.7u
Gemini 3.1 Pro
Gemini 3.1 Pro 77–92 · 46%
-36.4u
Gemini 2.5 Flash-Lite
Gemini 2.5 Flash-Lite 532–640 · 45%
-452.6u
Claude Haiku 4.5
Claude Haiku 4.5 672–829 · 45%
-671.1u
Gemini 2.5 Pro
Gemini 2.5 Pro 108–151 · 42%
-78.6u

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: 3c5aa2b83d8b8aa1…
Kickoff
Fri, Jul 3 · 20:05 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": 9368,
        "sport": "baseball",
        "venue": null,
        "league": "MLB",
        "starts_at": "2026-07-03T20:05:00+00:00",
        "starts_at_human": "Fri, 03 Jul 2026 20:05:00 GMT"
    },
    "teams": {
        "away": "St.Louis Cardinals",
        "home": "Chicago Cubs"
    },
    "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": "WLLLL",
            "record": "1W-0D-4L",
            "scored": 10,
            "matches": 5,
            "conceded": 23
        },
        "home_form": {
            "last": "WWWLW",
            "record": "4W-0D-1L",
            "scored": 21,
            "matches": 5,
            "conceded": 16
        },
        "rest_days": {
            "away": 5,
            "home": 3
        }
    },
    "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 →