Los Angeles Angels vs Tampa Bay Rays
Final: 4 – 3
Verifiable brief
Identical prompt sent to every AI · SHA-256 verified
hash:
1cf16d43ff73a4e2…
- Sport
- Sat, Jun 13 · 01:38 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": 2612,
"sport": "baseball",
"venue": null,
"league": "MLB",
"starts_at": "2026-06-13T01:38:00+00:00",
"starts_at_human": "Sat, 13 Jun 2026 01:38:00 GMT"
},
"teams": {
"away": "Tampa Bay Rays",
"home": "Los Angeles Angels"
},
"version": "v1",
"built_at": "2026-06-12T02:16:35+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
4 markets · 6 models picked
Who picked what
15 models × 4 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.
|
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).
|
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
|
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
|
|
|---|---|---|---|---|---|
|
Claude Opus 4.7 FlagshipAnthropic · 4-5 -1.2u |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Claude Opus 4.6 FlagshipAnthropic · 5-5 -0.3u |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Claude Opus 4 FlagshipAnthropic |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Claude Sonnet 4.6 FlagshipAnthropic · 125-128 -87.1u |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Claude Haiku 4.5 Anthropic · 168-149 -107.9u |
52%
Over 8.5
V
|
48%
Los Angeles Angels -1.5
V
|
54%
Under 4.5
V
|
55%
Los Angeles Angels
W
|
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
52%
Over 8.5 MLB totals in June typically hover around 8–9 runs per game depending on ballpark and pitcher matchups. The Angels play in a relatively neut...
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%
Los Angeles Angels -1.5 Home-field advantage suggests a small Angels edge, but -1.5 is a tight spread reflecting competitive balance. The Rays are a well-managed fr...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
54%
Under 4.5 Early-inning totals typically see fewer runs than full-game lines due to pitcher freshness and lineup momentum building gradually. Without k...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
55%
Los Angeles Angels The Angels are favored at home in late June 2026. Without access to current 2026 season standings, recent form, or injury reports, this pred... |
|||||
|
GPT-5 FlagshipOpenai |
Flagship picks across 4 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.
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.
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
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. |
|||||
|
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.
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.
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
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. |
|||||
|
o3 FlagshipOpenai |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Grok 4 Heavy FlagshipXai |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Grok 4 Fast Xai · 112-170 -91.3u |
51%
over
V
|
50%
Los Angeles Angels
V
|
52%
Los Angeles Angels
V
|
53%
Los Angeles Angels
L
|
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
51%
over Typical MLB scoring environments favor overs slightly in interleague play. Training data shows both lineups capable of moderate run producti...
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%
Los Angeles Angels Run-line splits are near even based on historical home/away performance. No meaningful edge emerges from outdated team profiles. All inputs...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
52%
Los Angeles Angels Home teams tend to perform marginally better early in games per long-term MLB trends. Both starters' past first-five results were balanced....
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
53%
Los Angeles Angels Both teams have shown inconsistent results in recent seasons per training data through 2025. Angels hold a slight home advantage historicall... |
|||||
|
Gemini 2.5 Pro FlagshipGoogle · 4-7 -1.8u |
Flagship picks across 4 markets — unlock with Pro
Get Pro
|
||||
|
Gemini 2.5 Flash Google · 135-151 -121.4u |
55%
Under 8.5 Runs
W
|
55%
Tampa Bay Rays -1.5
V
|
55%
Tampa Bay Rays Lead
V
|
58%
Tampa Bay Rays
L
|
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
55%
Under 8.5 Runs My training data (through 2025-09) suggests the Tampa Bay Rays typically play in lower-scoring games due to their strong pitching and defens...
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).
55%
Tampa Bay Rays -1.5 Given the general strength disparity observed in training data (through 2025-09), the Tampa Bay Rays are expected to control the game and se...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
55%
Tampa Bay Rays Lead The Tampa Bay Rays typically feature solid starting pitching, which gives them an edge in the early innings. Combined with their ability to...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
58%
Tampa Bay Rays Based on historical team performance from training data (through 2025-09), the Tampa Bay Rays have generally been a more consistent and well... |
|||||
|
Gemini 2.5 Flash-Lite Google · 65-141 -96.1u |
52%
over
V
|
53%
Tampa Bay Rays
V
|
54%
Tampa Bay Rays
V
|
55%
Tampa Bay Rays
L
|
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
52%
over Without specific pitching matchups or park factors from live data, it's difficult to predict an exact total. However, the historical average...
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%
Tampa Bay Rays Given the slight edge for the Rays in head-to-head, they are marginally more likely to cover a standard spread. This prediction is based on...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
54%
Tampa Bay Rays The Rays' historical pitching strength often translates to better performance in the early innings. Assuming typical performance trends, the...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
55%
Tampa Bay Rays Based on training data, the Tampa Bay Rays generally have a stronger historical performance and pitching advantage compared to the Los Angel... |
|||||
|
DeepSeek V3 Deepseek · 136-147 -106.2u |
52%
Over
L
|
65%
Los Angeles Angels +1.5
V
|
55%
Tampa Bay Rays
V
|
58%
Tampa Bay Rays
L
|
|
|
Over / Under
?
Over / Under
Over / Under total points. Will the combined score be above or below the line.
52%
Over Both teams have potent offenses capable of scoring, and Anaheim's ballpark favors run production. However, uncertainty about starting pitche...
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).
65%
Los Angeles Angels +1.5 The Angels, even when losing, tend to keep games close at home. Spreads of +1.5 give them a strong chance to cover even in a loss. Training...
First 5 innings
?
First 5 innings
First five innings result. Standings after five innings, regardless of late drama.
55%
Tampa Bay Rays Rays typically have strong starting pitching, which often gives them an edge in the first five innings. The Angels' bullpen is unreliable, b...
Match winner
?
Match winner
Match winner. Pick the team that wins in regular time (or who advances in cup formats).
58%
Tampa Bay Rays Based on training data through 2025-09, the Rays have a stronger overall roster and deeper pitching staff, while the Angels rely heavily on... |
|||||
|
Consensus |
over 2/6 |
Tampa Bay Rays -1.5 2/6 |
Tampa Bay Rays 2/6 |
Tampa Bay Rays 4/6 |
|
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.