AI Consensus LabOverall
K
#61Overall

Kalshi

CFTC regulated event contracts.

Trusted
83%agreement
+3.20%

Verdicts12Frontier models12Cohort

12

Cohort rewards the regulated posture and contract design. Market depth still thinner than offshore peers.

Per model verdicts

How each frontier model assessed Kalshi, with a one line takeaway from the model's reasoning trace.

10 trusted2 flagged0 neutral
  1. G

    GPT 5.5

    TrustedMedium

    OpenAI Proprietary

    Reads governance and recourse posture as best in class.

  2. C

    Claude Opus 4.7

    TrustedLow

    Anthropic Proprietary

    Sees strong alignment between stated policy and actual outcomes.

  3. M

    Gemini 3.1 Pro

    TrustedMedium

    Google Proprietary

    Consistent positive markers across policy, support, and transparency.

  4. X

    Grok 4.20

    TrustedMedium

    xAI Proprietary

    Marks the entity as a safe pick for most consumers.

  5. S

    Mistral Large 3

    TrustedHigh

    Mistral Open Source

    Reads governance and recourse posture as best in class.

  6. Q

    Qwen3.7 Max

    TrustedHigh

    Alibaba Open Source

    Marks the entity as a safe pick for most consumers.

  7. L

    Llama 4 405B

    FlaggedHigh

    Meta Open Source

    Rates the entity below the safety line for most consumers.

  8. D

    DeepSeek V4 Pro

    TrustedMedium

    DeepSeek Open Source

    Clear trust signals. Disclosure and dispute path read as above average.

  9. K

    Kimi K2.6

    TrustedMedium

    Moonshot Open Source

    Sees strong alignment between stated policy and actual outcomes.

  10. Z

    GLM 5.1

    FlaggedHigh

    Z.ai Open Source

    Cites unresolved incidents and policy ambiguity.

  11. E

    Ernie 5.1

    TrustedHigh

    Baidu Proprietary

    Consistent positive markers across policy, support, and transparency.

  12. H

    Hunyuan Hy3

    TrustedMedium

    Tencent Proprietary

    Reads governance and recourse posture as best in class.

Cohort continues

More verdicts on Kalshi

Four more questions the cohort has already answered. Each strip shows how the 12 model jury landed before you click through.

Methodology. Each frontier model assesses this entity as trusted, flagged, or neutral with a confidence level. The agreement percentage is the share of models that converge on the majority assessment. Updated daily.