Baltimore Orioles vs San Diego Padres
Final: 3 – 9
Verifiable brief
Identical prompt sent to every AI · SHA-256 verified
hash:
19856326e5ab0120…
- Sport
- Sat, Jun 13 · 20:05 GMT+0000
- Markets
- h2h · totals · spreads · first_five_innings
- Source
- The Odds API · live
- 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": 2669,
"sport": "baseball",
"venue": null,
"league": "MLB",
"starts_at": "2026-06-13T20:05:00+00:00",
"starts_at_human": "Sat, 13 Jun 2026 20:05:00 GMT"
},
"teams": {
"away": "San Diego Padres",
"home": "Baltimore Orioles"
},
"version": "v1",
"built_at": "2026-06-12T19:15:05+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.
AI predictions
5 markets · 6 models picked
Who picked what
15 models × 5 markets · click a row to see reasoning
| Model |
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.
|
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).
|
First five innings over 4.5
?
First five innings over 4.5
Market explanation coming soon.
|
|
|---|---|---|---|---|---|---|
|
Claude Opus 4.7 FlagshipAnthropic · 4-5 -1.2u |
Flagship picks across 5 markets — unlock with Pro
Get Pro
|
|||||
|
Claude Opus 4.6 FlagshipAnthropic · 5-5 -0.3u |
Flagship picks across 5 markets — unlock with Pro
Get Pro
|
|||||
|
Claude Opus 4 FlagshipAnthropic |
Flagship picks across 5 markets — unlock with Pro
Get Pro
|
|||||
|
Claude Sonnet 4.6 FlagshipAnthropic · 125-128 -87.1u |
Flagship picks across 5 markets — unlock with Pro
Get Pro
|
|||||
|
Claude Haiku 4.5 Anthropic · 168-149 -107.9u |
52%
Over 8.5
W
|
55%
Under 4.5 (First Five Innings Total)
V
|
54%
San Diego Padres +1.5
V
|
58%
Baltimore Orioles
L
|
— | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
52%
Over 8.5 Both the Orioles and Padres possess capable offenses and have shown ability to score runs consistently. June weather in Baltimore is typical...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
55%
Under 4.5 (First Five Innings Total) Early-inning totals typically see lower run production than full-game totals as batters adjust to opposing pitchers and defenses are fresh....
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).
54%
San Diego Padres +1.5 While the Orioles are favored at home, a +1.5 spread for the Padres offers modest value. The Padres have a strong core and the spread sugges...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
58%
Baltimore Orioles As of my training data (September 2024), the Baltimore Orioles were a competitive AL East team with strong recent form and a solid roster. T...
First five innings over 4.5
?
First five innings over 4.5
Market explanation coming soon.
No pick on this market. |
||||||
|
GPT-5 FlagshipOpenai |
Flagship picks across 5 markets — unlock with Pro
Get Pro
|
|||||
|
GPT-5 Mini Openai · 30-17 +24.4u |
— | — | — | — | — | |
|
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.
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.
First five innings over 4.5
?
First five innings over 4.5
Market explanation coming soon.
No pick on this market. |
||||||
|
GPT-4o Mini Openai · 34-47 -25.2u |
— | — | — | — | — | |
|
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.
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.
First five innings over 4.5
?
First five innings over 4.5
Market explanation coming soon.
No pick on this market. |
||||||
|
o3 FlagshipOpenai |
Flagship picks across 5 markets — unlock with Pro
Get Pro
|
|||||
|
Grok 4 Heavy FlagshipXai |
Flagship picks across 5 markets — unlock with Pro
Get Pro
|
|||||
|
Grok 4 Fast Xai · 112-170 -91.3u |
52%
over
V
|
51%
Baltimore Orioles
V
|
49%
home_-1.5
V
|
53%
Baltimore Orioles
L
|
— | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
52%
over Training data through 2025-09 provides no 2026 season information for these clubs. Both lineups historically feature power hitters that push...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
51%
Baltimore Orioles Training data through 2025-09 provides no 2026 season information for these clubs. Baltimore starting pitchers have shown better early-innin...
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).
49%
home_-1.5 Training data through 2025-09 provides no 2026 season information for these clubs. Orioles home run differential has been marginally positiv...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
53%
Baltimore Orioles Training data through 2025-09 provides no 2026 season information for these clubs. Baltimore holds a slight home edge in typical interleague...
First five innings over 4.5
?
First five innings over 4.5
Market explanation coming soon.
No pick on this market. |
||||||
|
Gemini 2.5 Pro FlagshipGoogle · 4-7 -1.8u |
Flagship picks across 5 markets — unlock with Pro
Get Pro
|
|||||
|
Gemini 2.5 Flash Google · 135-151 -121.4u |
55%
Over 8.5
W
|
45%
Baltimore Orioles
V
|
53%
Baltimore Orioles -1.5
V
|
58%
Baltimore Orioles
L
|
— | |
|
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 for this 2026 game, the prediction leans on the historical offensive capabilities of both teams and the l...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
45%
Baltimore Orioles The Orioles are predicted to hold an advantage after the first five innings, typically the domain of starting pitchers and early offensive s...
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%
Baltimore Orioles -1.5 Aligning with the moneyline prediction, the Orioles are expected to not just win but secure a victory by at least two runs, leveraging their...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
58%
Baltimore Orioles This prediction relies on the Baltimore Orioles' general competitive strength and the significant advantage of playing at home. Given that s...
First five innings over 4.5
?
First five innings over 4.5
Market explanation coming soon.
No pick on this market. |
||||||
|
Gemini 2.5 Flash-Lite Google · 65-141 -96.1u |
52%
over
W
|
— |
53%
San Diego Padres
V
|
55%
San Diego Padres
L
|
51%
over
V
|
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
52%
over Without access to current pitching matchups or recent offensive/defensive trends for these teams in 2026, I am relying on general MLB scorin...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
No pick on this market.
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%
San Diego Padres Given the lack of specific 2026 season data, and assuming a close contest as is typical in MLB, predicting a cover on the spread is challeng...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
55%
San Diego Padres My training data does not include real-time information for this specific MLB game in 2026. However, based on general team strengths and typ...
First five innings over 4.5
?
First five innings over 4.5
Market explanation coming soon.
51%
over Predicting first five innings performance is highly dependent on starting pitchers and early offensive momentum, information not available f... |
||||||
|
DeepSeek V3 Deepseek · 136-147 -106.2u |
52%
Under
V
|
56%
Baltimore Orioles
V
|
60%
San Diego Padres +1.5
V
|
55%
Baltimore Orioles
L
|
— | |
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
52%
Under Both teams have had mixed offensive output recently, and the starting pitchers are capable of limiting runs early. The Orioles' ace Corbin B...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
56%
Baltimore Orioles The Orioles have a strong starting pitching advantage with Corbin Burnes, who historically dominates early innings. Baltimore's lineup typic...
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).
60%
San Diego Padres +1.5 Even though the Orioles are favored, the Padres have been competitive in most games and their bullpen can keep deficits close. San Diego's r...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
55%
Baltimore Orioles The Orioles have a strong home record at Camden Yards, while the Padres have been inconsistent on the road in 2026. Baltimore's lineup is de...
First five innings over 4.5
?
First five innings over 4.5
Market explanation coming soon.
No pick on this market. |
||||||
|
Consensus |
Over 8.5 2/6 |
Baltimore Orioles 3/5 |
Baltimore Orioles -1.5 2/6 |
Baltimore Orioles 5/6 |
over 1/1 |
|
Ask the AIs · Post-match analysis
Reverse-engineer the match
Ask any AI to explain what happened or grade the consensus call.
Sign in to ask the AIs about this match. Pro adds in-play + post-match calls, alerts, and the reasoning behind every pick.
Get the AI consensus before kickoff
Free. Pre-match alert per AI + see your picks graded as results land.