The Coalition
Group bets Tail Research Find a pool Sign in Sign up
MLS · Every game Claude picked

Claude’s record

Before the bigger games Claude, ChatGPT and Grok each take a side on who wins, the spread and the over/under, from the same facts. Here’s every one of Claude’s picks and how it went, graded on the line it saw when it picked. Tap a game for its page and the result.

ClaudeAnthropic 1–0 100%–1–0 100% ChatGPTOpenAI ––– GrokxAI –––

Members vs the AIs

Members’ picks on the winner, the spread and the total of the games the AIs picked, the last 30 days, ranked from 10 picks with a result. No member is ahead of all three AIs yet.

  1. 1 GrokxAI 43–2960%
  2. 2 ChatGPTOpenAI 42–3058%
  3. 3 ClaudeAnthropic 669–504–357%
  4. 4 Xavier Kelly 154–12855%
Picking winners
1–0
100% right · 1 pick
Against the spread
—
Once a game it picked is over
Over / under
1–0
100% right · 1 pick

Is Claude as sure as it says?

Its graded picks by how sure it said it was. A well-sized pick at 70% hits about 70% of the time; the gold line is what it said.

Said 50–59% 100% hit · 1–0
Said 60–69% 100% hit · 1–0
Said 70–80% No picks yet

How it went 1 game

Sun, Nov 1 1 game
FinalHouston Dynamo FCHouston1at Portland TimbersPortland3WinnerPOR60%HitSpreadPOR55%No lineTotalOver 2.555%Hit2 of 2

The AI (Claude) picks every NFL game and other leagues’ bigger games (ranked matchups, national TV, games Coalition members are picking) the day before; ChatGPT and Grok pick the same games from the same facts and the same instructions. Each pick is graded on the line it saw; a pick written again after the line moved is graded on the newer line. A tie on the winner is a push, except a draw in soccer, which is a miss. Times are Eastern. Research, not betting advice. How we grade

Plan your picks with your groupPick together, split the slips, track every dollar. Free.