WIL 1-2 PEC · 51% HAM 1-0 BOR · 47% BRI 1-0 CAM · 46% VEN 1-1 UDI · 42% TOU 2-1 STR · 53% STA 2-1 SKB · 49% OXF 0-2 LEI · 61% EVE 1-0 COV · 53% SEV 1-0 ALA · 49% DER 1-1 BOL · 42% FAM 1-1 ARO · 43% IND 1-0 DEP · 52% SAN 1-0 PLA · 46% UNI 0-1 VEL · 46% WIL 1-2 PEC · 51% HAM 1-0 BOR · 47% BRI 1-0 CAM · 46% VEN 1-1 UDI · 42% TOU 2-1 STR · 53% STA 2-1 SKB · 49% OXF 0-2 LEI · 61% EVE 1-0 COV · 53% SEV 1-0 ALA · 49% DER 1-1 BOL · 42% FAM 1-1 ARO · 43% IND 1-0 DEP · 52% SAN 1-0 PLA · 46% UNI 0-1 VEL · 46%
— AI vs prediction markets

Can AI beat Polymarket and Kalshi?

Every day ten AI models forecast the most-traded questions on Polymarket and Kalshi, without seeing the price. When each market settles, we score who picked the right outcome.

Settled
124
AI right
82
Market right
97
Brier AI / market
0.209 / 0.140

Where the AIs disagree with the market

Open questions

Recently settled

Which AI beats the market most?

# Model Brier Right side Beat market
1 GPT-5.6 Luna 0.206 64% 42/124
2 Kimi K3 0.206 69% 46/124
3 Mistral Medium 3.5 0.208 64% 35/111
4 DeepSeek V4 Pro 0.212 65% 52/124
5 GLM 5.3 0.216 67% 45/124
6 Qwen 3.8 Max 0.216 65% 46/124
7 Meta Muse Spark 1.3 0.216 62% 6/13
8 Gemini 3.8 Flash 0.217 66% 42/124
9 Grok 4.6 0.217 65% 30/124
10 MiMo V2.5 Pro 0.220 64% 38/124
11 Claude Sonnet 5 0.240 65% 39/124

Market Brier on the same questions: 0.140.

FAQ

Can AI beat Polymarket and Kalshi?

After 124 settled markets, the AI panel picked the right outcome 82 times and the market 97 times. Brier score (lower is better): AI 0.209, market 0.140.

How does this work?

Every day TuringStats takes the busiest questions on Polymarket and Kalshi. Ten AI models (GPT, Claude, Gemini, Grok, DeepSeek and more) read the resolution rules and a fresh web news brief, then each gives its own chance of YES. They never see the market price.

How are the AI and the market graded?

When a market settles we compare the AI panel average with the market price at the moment the AIs voted. A side picked the right outcome when it gave the winning side more than 50%. Across many questions we also use the Brier score, which rewards confidence when it is right; always saying 50% scores 0.25.

Can I ask the AI models my own question?

Yes. Ask Multiple AI sends one question to all ten models at once and shows each answer side by side.

Is this betting advice?

No. TuringStats does not offer trading or wagering and is not affiliated with Polymarket or Kalshi.

Have your own question? Ask all ten AIs at once.