SFSan Francisco Giants
WLWLL
L2
CRColorado Rockies
LWLWL
Sun 12 Jul, 8:05 pm UTC
10:05 PM
Starts · GMT+2
2/28 AIs back San Francisco Giants · 58.5%
AI vs AI: 7 models predict every match.See which AI predicts baseball best — graded in public. Sign up free to read every model's call, then make them predict your matches.Start free
Value readAI consensus vs the market
On San Francisco Giants
AI consensus58.5%
Market implied59.8%
-1.3%
AI edge

The market rates San Francisco Giants higher than the AI consensus does — no edge on this pick.

The AI verdict
7 frontier models · 28 calls
ModelMatch winnerOver / Under
ConsensusSan Francisco Giants2/7 modelsOver 8.51/3 models
Grok 4 FastFLAGSHIPxai · 48% · 4,469 graded · San Francisco Giants53%Under56%
GPT-5 Miniopenai · 53% · 1,424 graded · San Francisco Giants64%—
DeepSeek V3deepseek · 46% · 5,379 graded · San Francisco Giants60%Under 8.555%
Claude Haiku 4.5anthropic · 48% · 2,333 graded · Colorado Rockies58%Over 8.562%
Gemini 2.5 Flash-Litegoogle · 46% · 3,706 graded · Colorado Rockies55%—
GPT-4o Miniopenai · 54% · 2,296 graded · Colorado Rockies55%—
Gemini 2.5 Flashgoogle · 48% · 4,265 graded · Colorado Rockies52%—

In-play snapshots

Match is live — run a model on the current state for an in-play read. Snapshots don't change the locked pre-match picks or the leaderboard.

These runs get a light read (recent form + market line). Pro feeds each model the full dossier — records, head-to-head, standings, profiles & line movement, so it picks on real evidence. Upgrade →
Grok 4 Fast
DeepSeek V3
GPT-5 Mini
Claude Haiku 4.5
GPT-4o Mini
Gemini 2.5 Flash
Gemini 2.5 Flash-Lite

You're only charged when a model locks a prediction; technical failures are refunded automatically. No wagers, no payouts — we make the AIs predict and grade who's right.

Loading the model panel…
Market implied probabilityPolymarket · live
San Francisco Giants
57%1.67
3
Colorado Rockies
43%2.24
4
Order bookPolymarket CLOB · live
Loading live book…
Recent tradesPolymarket · live
Loading trades…
1X2Over/UnderBoth teams to scoreDouble chance

Moneyline (1X2) — best available price, with the market's implied probability.

OutcomeDecimalImpliedAI edge
San Francisco Giants1.6759.8%-1.3%
Colorado Rockies2.2444.6%—

AI edge = the model consensus' probability minus the market's implied probability on the same outcome. Positive edge means the AIs rate it more likely than the book.

System instruction

You are a sports forecasting model. You are given identical structured facts about one match. Make an honest, calibrated prediction. You may not browse; use only the facts provided. Do not hedge — commit to one pick and a probability.

User brief (JSON) — sent byte-for-byte to every model

{
  "match": {
    "home": "San Francisco Giants",
    "away": "Colorado Rockies",
    "sport": "baseball",
    "league": "MLB",
    "kickoff_utc": "2026-07-12T20:05:00.000Z",
    "venue": "Oracle Park"
  },
  "market": {
    "type": "moneyline",
    "options": [
      "home",
      "away"
    ]
  },
  "bookmaker_odds": {
    "home": "1.671",
    "draw": null,
    "away": "2.24"
  },
  "instructions": "Return your pick, a 0–100 confidence, a probability for each outcome, and one paragraph of reasoning."
}

A SHA-256 hash of this exact brief is stored on every prediction before kickoff. Nothing here changes after the result lands — hash it yourself to verify.

Every prediction here is made by a frontier AI model from the same structured brief, locked before kickoff with a timestamped integrity hash, and graded in public against the real result — losses included. No tips, no hindsight, no sportsbook money.