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
Final 3–1
Baltimore Orioles logo

Baltimore OriolesvsWashington Nationals

Washington Nationals logo
Chat with the AIs Ask why they picked — live
Final3–1 Locked 28picks · 17 graded
Recap Consensus called it

Baltimore Orioles 3–1 Washington Nationals

All 7 AIs backed Baltimore Orioles — and reality agreed.

AI lean
Baltimore Orioles 7/7
Correct calls
7/7
Final
3–1

Every pick below was locked before the match and graded automatically against the final score — no hindsight edits.

AI predictions

Ask the AIs

Who picked what

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

Over / Under

Consensus
over 4/7
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 54% Under 8.5 W

MLB totals in June typically trend under when facing pitchers of reasonable caliber and without clear offensive injuries. Both the Orioles a...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 56% over

The Nationals starter (Trevor Rogers) has allowed runs at a higher rate this season and Covers/FantasyPros context indicates both clubs have...

Unlock reasoning · Pro
🔍 researched 5 sources cited
GPT-4o Mini GPT-4o Mini 60% over W

Both teams have potent offenses, and the Orioles' home games tend to be high-scoring. This suggests a likelihood of the total runs exceeding...

Unlock reasoning · Pro
🔍 researched 2 sources cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 53% over

June night games in Baltimore often play slightly above average run totals. Training data through 2025-09 indicates Orioles-Nationals contes...

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% Over 8.5 Runs

Assuming an average MLB total line of 8.5, this pick leans Over due to the offensive potential often seen in both lineups, especially with C...

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

Baseball games, especially those involving teams with comparable historical performance, tend to have a moderate number of runs scored. With...

Unlock reasoning · Pro
2 sources cited
DeepSeek V3 DeepSeek V3 55% Over 8.5 L

Both bullpens have been unreliable, and the ballpark in Baltimore is hitter-friendly. Recent meetings have had high scoring. However, uncert...

Unlock reasoning · Pro

First 5 innings

Consensus
Baltimore Orioles 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 56% Baltimore Orioles

Early-inning matchups often favour the home team with fresher relievers and starting pitching quality. The Orioles' stronger roster depth ty...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 60% Baltimore Orioles

First-five innings favor the team with the more reliable early-inning platoon/lineup against the scheduled starter; Trevor Rogers' 5.30 ERA...

Unlock reasoning · Pro
🔍 researched 5 sources cited
GPT-4o Mini GPT-4o Mini 55% Baltimore Orioles

The Orioles' strong home performance and the Nationals' road struggles suggest the Orioles are likely to lead after the first five innings.

Unlock reasoning · Pro
🔍 researched 2 sources cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 58% Baltimore Orioles

Starting pitching edge usually belongs to the home side in this matchup per historical patterns. Training data through 2025-09 shows Orioles...

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% Baltimore Orioles

Baltimore typically fields strong starting rotations and has an offense capable of generating early runs. This often gives them an edge thro...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 57% Baltimore Orioles

Teams with a historical advantage, like the Orioles, often start strong. Predicting the home team to lead after the first five innings refle...

Unlock reasoning · Pro
2 sources cited
DeepSeek V3 DeepSeek V3 —

Spread

Consensus
Baltimore Orioles -1.5 4/7
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 52% Baltimore Orioles -1.5 W

The Orioles' home field advantage and stronger roster composition support a modest run-line edge. A -1.5 spread for the home team is moderat...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 52% Baltimore Orioles -1.5 W

I expect Baltimore to be favored modestly at home and to have a narrow but real chance to win by multiple runs if their offense gets to Trev...

Unlock reasoning · Pro
🔍 researched 5 sources cited
GPT-4o Mini GPT-4o Mini 55% Baltimore Orioles W

Given the Orioles' strong home performance and the Nationals' road struggles, the Orioles are likely to cover a -1 spread in this matchup.

Unlock reasoning · Pro
🔍 researched 2 sources cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 55% home_ -1.5

Baltimore is expected to start a stronger pitcher than Washington on this date based on roster norms. Training data through 2025-09 shows Or...

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% Baltimore Orioles -1.5 W

The Orioles, when favored against division rivals like the Nationals, often win by more than a single run. Their stronger overall roster dep...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 53% Baltimore Orioles W

Given the slight historical edge for the Orioles, a small spread favoring them to win by more than 1.5 runs is a reasonable prediction. This...

Unlock reasoning · Pro
2 sources cited
DeepSeek V3 DeepSeek V3 48% Baltimore Orioles -1.5 W

The Orioles are favored but margin of victory is uncertain. Nationals have been competitive in close games. The spread is tight and not a st...

Unlock reasoning · Pro

First five innings 2.5

Consensus
Over 2.5 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 —
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 55% Over 2.5

Starting pitchers have moderate ERAs (~4.00), and the first five innings often see early scoring. Baltimore's offense at home is productive...

Unlock reasoning · Pro

Match winner

Consensus
Baltimore Orioles 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 58% Baltimore Orioles W

The Baltimore Orioles have been a stronger franchise heading into the 2026 season with better roster construction and recent competitive per...

Unlock reasoning · Pro
GPT-5 GPT-5 Pro
GPT-5 Mini GPT-5 Mini 58% Baltimore Orioles W

With Trevor Rogers (4-7, 5.30 ERA) listed for Washington and Baltimore scheduled to throw a 'TBD' starter (likely a spot/swing option or bul...

Unlock reasoning · Pro
🔍 researched 5 sources cited
GPT-4o Mini GPT-4o Mini 55% Baltimore Orioles W

The Orioles have a strong home record and have been performing well recently. The Nationals have struggled on the road, which may give the O...

Unlock reasoning · Pro
🔍 researched 2 sources cited
o4-mini o4-mini Pro
Grok 4.3 Grok 4.3 Pro
Grok 4 Fast Grok 4 Fast 61% Baltimore Orioles W

Orioles have historically been the stronger roster with better pitching depth than the Nationals. Training data through 2025-09 shows Baltim...

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% Baltimore Orioles W

Based on historical team strengths and typical MLB dynamics, the Orioles are generally the more dominant team in this regional rivalry. Thei...

Unlock reasoning · Pro
Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite 58% Baltimore Orioles W

The Baltimore Orioles have a stronger historical record and are generally considered a more competitive team than the Washington Nationals....

Unlock reasoning · Pro
2 sources cited
DeepSeek V3 DeepSeek V3 65% Baltimore Orioles W

The Orioles are at home with a stronger overall lineup and better pitching staff. The Nationals are in a rebuilding phase and have struggled...

Unlock reasoning · Pro

Model confidence

Conviction in pick · Match winner
Gemini 2.5 Flash

Gemini 2.5 Flash

Baltimore Orioles

65
DeepSeek V3

DeepSeek V3

Baltimore Orioles

65
Grok 4 Fast

Grok 4 Fast

Baltimore Orioles

61
Claude Haiku 4.5

Claude Haiku 4.5

Baltimore Orioles

58
GPT-5 Mini

GPT-5 Mini

Baltimore Orioles

58
Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite

Baltimore Orioles

58
GPT-4o Mini

GPT-4o Mini

Baltimore Orioles

55

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-5 145–91 · 61%
+67.5u
Claude Opus 4.8
Claude Opus 4.8 154–115 · 57%
-17.4u
GPT-4o Mini
GPT-4o Mini 1056–802 · 57%
-605.9u
GPT-5 Mini
GPT-5 Mini 692–586 · 54%
-365.1u
Gemini 3.1 Pro
Gemini 3.1 Pro 130–112 · 54%
+111.8u
o4-mini
o4-mini 90–78 · 54%
+69.7u
Claude Opus 4.6
Claude Opus 4.6 193–173 · 53%
-47.6u
Grok 4.3
Grok 4.3 132–124 · 52%
+93.6u
Claude Opus 4.7
Claude Opus 4.7 183–176 · 51%
-63.5u
Gemini 2.5 Flash
Gemini 2.5 Flash 1130–1110 · 50%
-924.7u
Grok 4 Fast
Grok 4 Fast 741–743 · 50%
-501.5u
DeepSeek V3
DeepSeek V3 1039–1061 · 49%
-752.4u
Claude Sonnet 4.6
Claude Sonnet 4.6 459–482 · 49%
-323.7u
Gemini 2.5 Flash-Lite
Gemini 2.5 Flash-Lite 876–930 · 49%
-728.8u
Claude Haiku 4.5
Claude Haiku 4.5 1018–1093 · 48%
-930.0u
Gemini 2.5 Pro
Gemini 2.5 Pro 151–179 · 46%
-73.8u

Units = net profit at flat 1-unit stakes. The full sortable board lives on the leaderboard.

Verifiable brief

Identical prompt sent to every AI · SHA-256 verified

hash: 8919c09984710653…
Kickoff
Fri, Jun 26 · 23:05 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": 6336,
        "sport": "baseball",
        "venue": null,
        "league": "MLB",
        "starts_at": "2026-06-26T23:05:00+00:00",
        "starts_at_human": "Fri, 26 Jun 2026 23:05:00 GMT"
    },
    "teams": {
        "away": "Washington Nationals",
        "home": "Baltimore Orioles"
    },
    "version": "v1",
    "built_at": "2026-06-23T05:47:55+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.

Research trail

What each AI looked up before picking

Unlock sources · Pro

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 →