Boston Red Sox vs New York Yankees
Kickoff · Fri, Jun 26 · 23:10 GMT+0000
Verifiable brief
Identical prompt sent to every AI · SHA-256 verified
hash:
ddfe7e11fb561103…
- Kickoff
- Fri, Jun 26 · 23:10 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": 6341,
"sport": "baseball",
"venue": null,
"league": "MLB",
"starts_at": "2026-06-26T23:10:00+00:00",
"starts_at_human": "Fri, 26 Jun 2026 23:10:00 GMT"
},
"teams": {
"away": "New York Yankees",
"home": "Boston Red Sox"
},
"version": "v1",
"built_at": "2026-06-23T05:48:18+00:00",
"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.
Your call
Who wins? One tap, no signup.
AI predictions
4 markets · 6 models picked
Who picked what
16 models × 4 markets · click a row to see reasoning
| Model |
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
|
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
|
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
|
|
|---|---|---|---|---|---|
Claude Opus 4.7 FlagshipAnthropic |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Claude Opus 4.6 FlagshipAnthropic |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Claude Opus 4.8 FlagshipAnthropic |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Claude Sonnet 4.6 FlagshipAnthropic |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Claude Haiku 4.5 Anthropic |
50%
Boston Red Sox -1.5 |
52%
Boston Red Sox |
55%
Over 8.5 |
51%
Boston Red Sox |
|
|
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
50%
Boston Red Sox -1.5 With no live injury data, starting pitcher matchups, or current form, this market is effectively a coin flip favoring home advantage. Boston...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
52%
Boston Red Sox As of my training cutoff (April 2025), both teams are competitive AL East rivals with historical parity. Boston has shown resilience at home...
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
55%
Over 8.5 Red Sox–Yankees matchups historically produce moderate-to-high scoring games due to both teams' lineup strength and the competitive nature o...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
51%
Boston Red Sox First five innings outcomes are heavily skewed by starting pitchers and early lineup performance. Boston's home advantage and batting order... |
|||||
GPT-5 FlagshipOpenai |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
GPT-5 Mini Openai |
— | — | — | — | |
|
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
No pick on this market.
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
No pick on this market.
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
No pick on this market.
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
No pick on this market. |
|||||
|
GPT-4o Mini Openai |
50%
New York Yankees |
60%
New York Yankees |
55%
under |
55%
New York Yankees |
|
|
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
50%
New York Yankees The Yankees' superior record and depth suggest they can cover the -1.5 spread, even with Judge's absence. ([baseball-reference.com](https://...
🔍 researched
4 sources cited
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
60%
New York Yankees The New York Yankees have a superior record (37-26) compared to the Boston Red Sox (27-35). Despite the Yankees' recent injury to Aaron Judg...
🔍 researched
4 sources cited
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
55%
under Both teams have strong pitching staffs, with the Yankees' ERA at 3.29 and the Red Sox's at 3.82. The absence of Aaron Judge may also impact...
🔍 researched
4 sources cited
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
55%
New York Yankees The Yankees' strong pitching and overall performance suggest they will lead after the first five innings. ([baseball-reference.com](https://...
🔍 researched
4 sources cited
|
|||||
|
o4-mini FlagshipOpenai |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
Grok 4.3 FlagshipXai |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Grok 4 Fast Xai |
51%
New York Yankees -1.5 |
53%
New York Yankees |
52%
over |
51%
New York Yankees |
|
|
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
51%
New York Yankees -1.5 Yankees favored by run line in similar road games historically. Bullpen depth supports holding leads late. Training data through 2024 used f...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
53%
New York Yankees Yankees maintain stronger overall roster depth and pitching staff per historical patterns through 2024. Red Sox home edge is offset by divis...
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
52%
over Rivalry games often feature higher run totals due to offensive matchups. Both lineups project for solid contact rates based on prior seasons...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
51%
New York Yankees Early game edge to Yankees starters in most historical outings. Red Sox offense slower to heat up on average. Training data through 2024 use... |
|||||
Gemini 3.1 Pro Flagship |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Gemini 2.5 Pro Flagship |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Gemini 2.5 Flash |
58%
Boston Red Sox +1.5 |
52%
New York Yankees |
55%
Over 8.5 |
38%
New York Yankees F5 ML |
|
|
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
58%
Boston Red Sox +1.5 Given the intense nature of the Red Sox-Yankees rivalry, games between these two teams are frequently close, often decided by one run. Betti...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
52%
New York Yankees Based on general historical MLB knowledge through my training data, the New York Yankees often maintain a slight edge in overall roster dept...
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
55%
Over 8.5 Without specific pitching matchups, I'm leaning Over 8.5 runs, assuming a typical high-stakes rivalry game between these two power-hitting t...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
38%
New York Yankees F5 ML The first five innings market heavily relies on starting pitching, which is unknown for this future game. However, based on the general dept... |
|||||
|
Gemini 2.5 Flash-Lite |
53%
New York Yankees |
55%
New York Yankees |
52%
over |
51%
over |
|
|
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
53%
New York Yankees Given the slight historical edge of the Yankees and the potential for a close but ultimately higher-scoring game, betting on the Yankees to...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
55%
New York Yankees Based on my training data through 2025-09, the Yankees generally hold a slight edge over the Red Sox in head-to-head matchups. This is often...
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
52%
over My training data suggests that games between these two historic rivals often feature a high number of runs due to potent offenses. Both team...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
51%
over Games between these two teams often start fast, with both offenses looking to establish an early lead. The potential for early runs from bot... |
|||||
DeepSeek V3 Deepseek |
48%
Boston Red Sox -1.5 |
55%
Boston Red Sox |
52%
Over 8.5 |
53%
Boston Red Sox |
|
|
Spread
?
Spread
Point spread. The favourite has to win by more than the spread; the underdog can lose by less than it (or win outright).
48%
Boston Red Sox -1.5 The Red Sox have narrow home wins, often by one run, making the spread a risky play. Yankees are competitive and often keep games close, so...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
55%
Boston Red Sox Based on training knowledge through 2025, the Red Sox have strong home form against the Yankees. Key injuries may affect both sides, but Bos...
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
52%
Over 8.5 Both offenses are potent, and Fenway Park tends to increase scoring. Pitching matchups historically lean high-scoring in this rivalry, with...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
53%
Boston Red Sox Boston's starting rotation at home tends to outduel Yankees' early, and they often lead after five innings. Recent first-five inning records... |
|||||
|
Consensus |
Boston Red Sox -1.5 2/6 |
New York Yankees 4/6 |
Over 8.5 3/6 |
Boston Red Sox 2/6 |
|
Spread
ConsensusBoston Red Sox -1.5 2/6
Claude Haiku 4.5
50%
Boston Red Sox -1.5
With no live injury data, starting pitcher matchups, or current form, this market is effectively a coin flip favoring home advantage. Boston...
GPT-5 Mini
—
GPT-4o Mini
50%
New York Yankees
The Yankees' superior record and depth suggest they can cover the -1.5 spread, even with Judge's absence. ([baseball-reference.com](https://...
Grok 4 Fast
51%
New York Yankees -1.5
Yankees favored by run line in similar road games historically. Bullpen depth supports holding leads late. Training data through 2024 used f...
Gemini 2.5 Flash
58%
Boston Red Sox +1.5
Given the intense nature of the Red Sox-Yankees rivalry, games between these two teams are frequently close, often decided by one run. Betti...
Gemini 2.5 Flash-Lite
53%
New York Yankees
Given the slight historical edge of the Yankees and the potential for a close but ultimately higher-scoring game, betting on the Yankees to...
DeepSeek V3
48%
Boston Red Sox -1.5
The Red Sox have narrow home wins, often by one run, making the spread a risky play. Yankees are competitive and often keep games close, so...
Match winner
ConsensusNew York Yankees 4/6
Claude Haiku 4.5
52%
Boston Red Sox
As of my training cutoff (April 2025), both teams are competitive AL East rivals with historical parity. Boston has shown resilience at home...
GPT-5 Mini
—
GPT-4o Mini
60%
New York Yankees
The New York Yankees have a superior record (37-26) compared to the Boston Red Sox (27-35). Despite the Yankees' recent injury to Aaron Judg...
Grok 4 Fast
53%
New York Yankees
Yankees maintain stronger overall roster depth and pitching staff per historical patterns through 2024. Red Sox home edge is offset by divis...
Gemini 2.5 Flash
52%
New York Yankees
Based on general historical MLB knowledge through my training data, the New York Yankees often maintain a slight edge in overall roster dept...
Gemini 2.5 Flash-Lite
55%
New York Yankees
Based on my training data through 2025-09, the Yankees generally hold a slight edge over the Red Sox in head-to-head matchups. This is often...
DeepSeek V3
55%
Boston Red Sox
Based on training knowledge through 2025, the Red Sox have strong home form against the Yankees. Key injuries may affect both sides, but Bos...
Over / Under
ConsensusOver 8.5 3/6
Claude Haiku 4.5
55%
Over 8.5
Red Sox–Yankees matchups historically produce moderate-to-high scoring games due to both teams' lineup strength and the competitive nature o...
GPT-5 Mini
—
GPT-4o Mini
55%
under
Both teams have strong pitching staffs, with the Yankees' ERA at 3.29 and the Red Sox's at 3.82. The absence of Aaron Judge may also impact...
Grok 4 Fast
52%
over
Rivalry games often feature higher run totals due to offensive matchups. Both lineups project for solid contact rates based on prior seasons...
Gemini 2.5 Flash
55%
Over 8.5
Without specific pitching matchups, I'm leaning Over 8.5 runs, assuming a typical high-stakes rivalry game between these two power-hitting t...
Gemini 2.5 Flash-Lite
52%
over
My training data suggests that games between these two historic rivals often feature a high number of runs due to potent offenses. Both team...
DeepSeek V3
52%
Over 8.5
Both offenses are potent, and Fenway Park tends to increase scoring. Pitching matchups historically lean high-scoring in this rivalry, with...
First 5 innings
ConsensusBoston Red Sox 2/6
Claude Haiku 4.5
51%
Boston Red Sox
First five innings outcomes are heavily skewed by starting pitchers and early lineup performance. Boston's home advantage and batting order...
GPT-5 Mini
—
GPT-4o Mini
55%
New York Yankees
The Yankees' strong pitching and overall performance suggest they will lead after the first five innings. ([baseball-reference.com](https://...
Grok 4 Fast
51%
New York Yankees
Early game edge to Yankees starters in most historical outings. Red Sox offense slower to heat up on average. Training data through 2024 use...
Gemini 2.5 Flash
38%
New York Yankees F5 ML
The first five innings market heavily relies on starting pitching, which is unknown for this future game. However, based on the general dept...
Gemini 2.5 Flash-Lite
51%
over
Games between these two teams often start fast, with both offenses looking to establish an early lead. The potential for early runs from bot...
DeepSeek V3
53%
Boston Red Sox
Boston's starting rotation at home tends to outduel Yankees' early, and they often lead after five innings. Recent first-five inning records...
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.
Ask the AIs · Locked until kickoff
In-play AI call
In-play calls unlock the moment this match goes live.
Sign in to ask the AIs about this match. Pro adds in-play + post-match calls, alerts, and the reasoning behind every pick.
Research trail
What each AI looked up before picking
-
0 tool calls · 0 sources
No live web access — picked from training-data knowledge.
-
4 tool calls · 4 sources
4 citations captured — unlock with Pro
-
0 tool calls · 0 sources
No live web access — picked from training-data knowledge.
-
0 tool calls · 0 sources
No live web access — picked from training-data knowledge.
-
0 tool calls · 0 sources
No live web access — picked from training-data knowledge.
-
0 tool calls · 0 sources
No live web access — picked from training-data knowledge.
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.