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 86h 56m
Detroit Tigers logo

Detroit TigersvsAthletics

Athletics logo
Chat with the AIs Ask why they picked — live
Kickoff Locked 28picks

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

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 62% Over 8.5

Oakland's pitching has hemorrhaged runs (35 allowed in 5 games = 7.0 RPG), and Detroit's offense is clicking (31 runs in 5 = 6.2 RPG). Even...

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

Springs' recent blowup starts increase run risk, but Skubal's strong recent work and Comerica Park's neutral-to-pitcher-friendly profile wit...

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

Both teams have relatively high team batting averages (.248 for the Athletics and .236 for the Tigers), suggesting potential for multiple ru...

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

Athletics poor pitching has allowed 35 runs in last 5 games while Tigers offense is averaging over 6 runs. Moderate rest and typical summer...

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% Under 8.5

Comerica Park is historically known as a pitcher-friendly ballpark, which tends to suppress overall run scoring. The Athletics have struggle...

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

Both teams have shown a tendency to score and concede a significant number of runs in their recent games. The Athletics have conceded 35 run...

Unlock reasoning · Pro
DeepSeek V3 DeepSeek V3 80% Over 2.5

Both teams have scored well recently (Athletics 20 runs in 5 games, Tigers 31). Over 2.5 hits in over 70% of MLB games historically. Without...

Unlock reasoning · Pro

Spread

Consensus
Detroit Tigers -1.5 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 55% Detroit Tigers -1.5

Detroit's form and run-differential advantage support a multi-run victory, but the -1.5 spread is tight enough to reflect real execution ris...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 55% Detroit Tigers -1.5

Given Skubal's form and Springs' tendency to allow multi-run innings in June, Detroit has a decent chance to win by multiple runs; the Tiger...

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

The Athletics' away record (22-21) is slightly better than the Tigers' home record (23-21). Additionally, the Athletics have a marginally hi...

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

Tigers hold home edge and better recent results; expect them to cover a 1.5-run spread against a struggling Athletics club. Training data th...

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% Detroit Tigers -1.5

Given the Detroit Tigers' superior recent form and home-field advantage, they are favored to win this matchup. Against a struggling Athletic...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 51% Athletics

Given the slight edge in recent form and rest for the Athletics, they are predicted to cover a small spread. The Tigers' home advantage is o...

Unlock reasoning · Pro
DeepSeek V3 DeepSeek V3 45% Detroit Tigers -1

Tigers are favorites but the spread requires a win by 2+. Their recent wins were by 1 or 2 runs, so a push is possible. The Athletics could...

Unlock reasoning · Pro

First 5 innings

Consensus
Detroit Tigers 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 60% Detroit Tigers

Early-inning play often mirrors overall matchup quality. Detroit's superior recent form and Oakland's poor pitching suggest the Tigers will...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 58% Detroit Tigers

Skubal's recent starts show he gets through the early innings with low run totals and high strikeout totals, while Springs has given up mult...

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

Both teams have relatively high team batting averages (.248 for the Athletics and .236 for the Tigers), suggesting potential for runs in the...

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 59% Detroit Tigers

Starting-pitcher and early-lineup advantages lean toward Detroit in the first five; Tigers' stronger recent form should manifest early. Trai...

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% Detroit Tigers

The Tigers' better overall recent form and home advantage should give them an early edge in the game. Assuming their starting pitching is at...

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

The Athletics' recent form, while inconsistent, shows a capacity to perform. Coupled with their rest advantage, they are slightly favored to...

Unlock reasoning · Pro
DeepSeek V3 DeepSeek V3 52% Detroit Tigers

Tigers have better recent form and home advantage, leading to a slight edge in the first half. Unknown starting pitchers reduce certainty, b...

Unlock reasoning · Pro

Match winner

Consensus
Detroit Tigers 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 68% Detroit Tigers

Detroit shows strong recent form (3W-2L) with a +6 run differential over the last 5, while Oakland is in freefall at 1W-4L with a -15 run di...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 62% Detroit Tigers

Detroit draws a clear pitching advantage: Tarik Skubal has been strong in his recent starts since returning from a rehab assignment while Je...

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

The Athletics have a slightly better away record (22-21) compared to the Tigers' home record (23-21). Additionally, the Athletics have score...

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% Detroit Tigers

Detroit Tigers enter with superior recent form (3W-2L, +6 run differential) versus Athletics' 1W-4L slump (-15 differential). Home rest adva...

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 62% Detroit Tigers

The Detroit Tigers enter this contest with better recent form, winning 3 of their last 5 games compared to the Athletics' 1 win. Playing at...

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

The Athletics have a slightly better recent record (3-2) compared to the Tigers (2-3) over their last five games, despite the Tigers scoring...

Unlock reasoning · Pro
DeepSeek V3 DeepSeek V3 55% Detroit Tigers

Tigers have better recent form (3-2 last 5) and home advantage. Athletics are struggling (1-4) and have worse rest advantage. However, start...

Unlock reasoning · Pro

Model confidence

Conviction in pick · Match winner
Claude Haiku 4.5

Claude Haiku 4.5

Detroit Tigers

68
GPT-5 Mini

GPT-5 Mini

Detroit Tigers

62
Grok 4 Fast

Grok 4 Fast

Detroit Tigers

62
Gemini 2.5 Flash

Gemini 2.5 Flash

Detroit Tigers

62
GPT-4o Mini

GPT-4o Mini

Athletics

55
DeepSeek V3

DeepSeek V3

Detroit Tigers

55
Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite

Athletics

52

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-5 123–84 · 59%
+72.2u
Claude Opus 4.8
Claude Opus 4.8 132–106 · 55%
-10.7u
GPT-4o Mini
GPT-4o Mini 773–656 · 54%
-459.9u
o4-mini
o4-mini 76–68 · 53%
+77.9u
GPT-5 Mini
GPT-5 Mini 551–500 · 52%
-280.7u
Claude Opus 4.6
Claude Opus 4.6 172–162 · 52%
-39.9u
Gemini 3.1 Pro
Gemini 3.1 Pro 110–104 · 51%
+114.9u
Claude Opus 4.7
Claude Opus 4.7 165–162 · 50%
-51.8u
Gemini 2.5 Flash
Gemini 2.5 Flash 889–909 · 49%
-723.7u
Grok 4 Fast
Grok 4 Fast 637–654 · 49%
-412.5u
Grok 4.3
Grok 4.3 111–115 · 49%
+99.0u
DeepSeek V3
DeepSeek V3 833–875 · 49%
-566.4u
Gemini 2.5 Flash-Lite
Gemini 2.5 Flash-Lite 696–747 · 48%
-545.8u
Claude Sonnet 4.6
Claude Sonnet 4.6 437–472 · 48%
-317.0u
Claude Haiku 4.5
Claude Haiku 4.5 821–949 · 46%
-786.0u
Gemini 2.5 Pro
Gemini 2.5 Pro 134–168 · 44%
-64.6u

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: 315a019545a5af29…
Kickoff
Tue, Jul 7 · 22:40 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": 10168,
        "sport": "baseball",
        "venue": null,
        "league": "MLB",
        "starts_at": "2026-07-07T22:40:00+00:00",
        "starts_at_human": "Tue, 07 Jul 2026 22:40:00 GMT"
    },
    "teams": {
        "away": "Athletics",
        "home": "Detroit Tigers"
    },
    "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": "LWLLL",
            "record": "1W-0D-4L",
            "scored": 20,
            "matches": 5,
            "conceded": 35
        },
        "home_form": {
            "last": "LWWWL",
            "record": "3W-0D-2L",
            "scored": 31,
            "matches": 5,
            "conceded": 25
        },
        "rest_days": {
            "away": 3,
            "home": 4
        }
    },
    "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 →