FCC 1-2 PHI · 50% COL 2-1 DCU · 54% NEW 1-0 CFM · 47% AL- 3-0 AL- · 65% COR 1-1 VIT · 42% SPO 1-2 FCD · 60% ST. 2-1 SAN · 49% ACM 1-1 INT · 42% EST 0-1 LEM · 44% AND 1-2 KVC · 43% SKB 0-2 UNI · 62% BAR 3-0 ALA · 64% AST 1-0 FUL · 46% DEP 0-0 TAL · 37% FCC 1-2 PHI · 50% COL 2-1 DCU · 54% NEW 1-0 CFM · 47% AL- 3-0 AL- · 65% COR 1-1 VIT · 42% SPO 1-2 FCD · 60% ST. 2-1 SAN · 49% ACM 1-1 INT · 42% EST 0-1 LEM · 44% AND 1-2 KVC · 43% SKB 0-2 UNI · 62% BAR 3-0 ALA · 64% AST 1-0 FUL · 46% DEP 0-0 TAL · 37%

Is AI better than prediction markets?

Updated 31 October 2026

Short answer

Not yet overall, but closer than you might think. Blind to the price, 10 AI models picked the right side 68.4% of the time against 73.7% for the market. On sports questions they picked 35 of 50 against the market's 35, their confident calls were right 18 of 20 times, and DeepSeek V4 Pro has beaten the market price on 40 questions.

Scoreboard

AI Market
Right side 68.4% 73.7%
Brier score (lower is better) 0.204 0.156
Sports questions, right side 35 of 50 35 of 50
Kalshi questions, right side 21 of 28 22 of 28

Why the AIs are handicapped

The models never see the price, the order book or what traders are betting; they only get the question and a short research brief. Markets also update every minute while the AI forecast is made once. Keeping up on the right side 68.4% of the time under those rules is the interesting result.

Follow the race

New questions are added every day and scored when they resolve. The live scoreboard shows every forecast, every model and who was closer.

Questions

Which AI model is best against the market?

DeepSeek V4 Pro: it has beaten the market price on 40 of 76 resolved questions.

How many questions have been scored?

76 so far; the record grows daily, so expect these numbers to move.

Ask 10 AIs before your next match.

Free picks for every match, every model graded, and your own questions answered by the whole council.