Ad Intelligence: see how your brand shows up in ChatGPT ads. Learn more →

How AI sees the 20 races that decide Congress

Every day we ask 4 AI assistants the same 10 neutral questions about 10 Senate and 10 House races. The same measurement EvidentlyAEO runs on your brand.

Assistants asked
4 across 20 races
Races where models split
11 of 20
AI agrees with Cook
12 of 20 races
Citations analyzed
5,204

AI answers collected Oct 23, 2026

Alaska Senate: Mary Peltola vs Dan Sullivan. AI models: toss-up / splitAKGeorgia Senate: Jon Ossoff vs Mike Collins. AI models lean DemocratGAKansas Senate: Adam Hamilton vs Roger Marshall. AI models: toss-up / splitKSMaine Senate: Troy Jackson vs Susan Collins. AI models lean DemocratMENorth Carolina Senate: Roy Cooper vs Michael Whatley. AI models lean DemocratNCTexas Senate: James Talarico vs Ken Paxton. AI models: toss-up / splitTXIowa Senate: Josh Turek vs Ashley Hinson. AI models: toss-up / splitIAMichigan Senate: Abdul El-Sayed vs Mike Rogers. AI models lean DemocratMINew Hampshire Senate: Chris Pappas vs John E. Sununu. AI models lean DemocratOhio Senate (special): Sherrod Brown vs Jon Husted. AI models: toss-up / splitOHNY-17NY-17 (Hudson Valley): Cait Conley vs Mike Lawler. AI models lean DemocratPA-8PA-8 (Scranton / Wilkes-Barre): Paige Cognetti vs Rob Bresnahan Jr.. AI models lean DemocratVA-2VA-2 (Virginia Beach): Elaine Luria vs Jennifer Kiggans. AI models: toss-up / splitAZ-6AZ-6 (Tucson / southeast Arizona): JoAnna Mendoza vs Juan Ciscomani. AI models lean DemocratCA-22CA-22 (Central Valley): Randy Villegas vs David Valadao. AI models lean DemocratCO-8CO-8 (north Denver suburbs): Manny Rutinel vs Gabe Evans. AI models: toss-up / splitWI-3WI-3 (western Wisconsin): Rebecca Cooke vs Derrick Van Orden. AI models lean DemocratOH-9OH-9 (Toledo): Marcy Kaptur vs Derek Merrin. AI models: toss-up / splitNC-1NC-1 (northeastern North Carolina): Donald Davis vs Laurie Buckhout. AI models lean DemocratTX-15TX-15 (South Texas): Bobby Pulido vs Monica De La Cruz. AI models: toss-up / split
lean DemocratAI models: toss-up / splitlean RepublicanRing = House district

Each dot is a seat. Tracked races are solid and colored by how most AI models lean; other seats are faded and colored by the party that holds them now. Select a tracked seat, a state or a pin to open the race.

What changed since Oct 22, 2026

Races where a model changed its call, the overall AI lean moved, or the tone toward a candidate shifted 5 points or more.

RaceAI leanChatGPTGoogle AI ModeGeminiPerplexity
Iowa SenateToss-upToss-upDeclinedToss-upToss-up
TX-15 (South Texas)Toss-up—DeclinedToss-upToss-up
Ohio Senate (special)Toss-upToss-upDeclined——
AZ-6 (Tucson / southeast Arizona)Lean DMendoza—Mendoza—
NY-17 (Hudson Valley)Lean D——Conley—
VA-2 (Virginia Beach)Toss-upToss-up———
CO-8 (north Denver suburbs)Toss-up—Toss-up——
Maine Senate——Toss-upJackson—
Alaska Senate———Toss-upPeltola
Kansas Senate—Marshall——Toss-up
Michigan Senate——El-Sayed——
New Hampshire Senate——Declined——
WI-3 (western Wisconsin)—Toss-up———
OH-9 (Toledo)—Merrin———
NC-1 (northeastern North Carolina)—Davis———

Each AI’s call, race by race

The same question, “Who is favored to win?”, asked to every assistant. Select a race for the full breakdown.

Senate

10 races

Senate races: candidates, AI lean, and each assistant’s call on who is favored to win
RaceCandidatesAIChatGPTGoogle AI ModeGeminiPerplexityOpen race
MaineTroy JacksonJacksonvsSusan CollinsCollins
North CarolinaRoy CooperCoopervsMichael WhatleyWhatley
OhioSherrod BrownBrownvsJon HustedHusted
TexasJames TalaricoTalaricovsKen PaxtonPaxton
IowaJosh TurekTurekvsAshley HinsonHinson
AlaskaMary PeltolaPeltolavsDan SullivanSullivan
MichiganAbdul El-SayedEl-SayedvsMike RogersRogers
GeorgiaJon OssoffOssoffvsMike CollinsCollins
New HampshireChris PappasPappasvsJohn E. SununuSununu
KansasAdam HamiltonHamiltonvsRoger MarshallMarshall
  • Each assistant’s call:
  • Democrat favored
  • Republican favored
  • Toss-up
  • Declined

Where the models disagree

Disagreement between assistants is part of the story: the races they split on, and who declines to call.

Where the models split most

How the four assistants divided on the most contested races.

Which AI won’t call races

Races where the assistant declined to say who is favored.

  • Google AI Mode12 of 20
  • Gemini1 of 20
  • Perplexity0 of 20
  • ChatGPT0 of 20

Non-answers across all questions: Google AI Mode 21, Gemini 7, Perplexity 72, ChatGPT 11.

What AI says voters care about

The issues the assistants list among voters’ top concerns, across all 20 races.

  1. 1

    Cost of living

    20/20

  2. 2

    Healthcare

    13/20

  3. 3

    Immigration

    9/20

  4. 4

    Jobs and the economy

    6/20

  1. 5

    Taxes and spending

    4/20

  2. 6

    Democracy and accountability

    4/20

  3. 7

    Social Security and Medicare

    3/20

  4. 8

    Trade and agriculture

    3/20

How many of the 20 races list each issue among voters’ top concerns, across the AI answers.

Who AI listens to

Every citation in today’s answers, grouped by type of source.

What AI cites, by model

5,204 citations across all 20 races.

All models
ChatGPT0% social and video · 380 citations
Google AI Mode31% social and video · 1874 citations
Gemini1% social and video · 939 citations
Perplexity0% social and video · 2011 citations
National news 16%Local news and other sites 55%Polls, wikis and voter guides 14%Social and video 11%Campaign and government 3%

Most cited sites

  • facebook.com378 cites20 races
  • youtube.com185 cites20 races
  • ballotpedia.org162 cites20 races
  • newsweek.com118 cites14 races
  • en.wikipedia.org97 cites17 races
  • yahoo.com80 cites19 races
  • localcandidates.org80 cites14 races
  • texastribune.org70 cites2 races
  • nytimes.com58 cites17 races
  • news.ballotpedia.org57 cites11 races
  • thehill.com51 cites11 races
  • washingtonpost.com48 cites8 races

Your brand gets asked these questions too

EvidentlyAEO runs this measurement for any brand: what each AI assistant says about you, which sources it trusts, and how that changes day to day.

Track your brand

How this works

Each morning we ask ChatGPT, Google AI Mode, Gemini and Perplexity the same 10 questions per race: 7 about the candidates and 3 about the parties. Every question names both candidates in neutral wording, and the order alternates so neither candidate is always first.

We then extract what each answer says: who it favors, the strengths and weaknesses it attributes to each candidate (with quotes checked against the original answer), the issues it says matter to voters, and the polls it cites. Attributes appear in headline views only when at least 2 models raise them. Allegations and investigations are never shown.

Races were chosen from Cook Political Report, Sabato’s Crystal Ball and Inside Elections ratings as the contests most likely to decide control of each chamber.

Cite this

Source: EvidentlyAEO AI Midterms Tracker, "How AI sees the 20 races that decide Congress," data as of Oct 23, 2026. https://evidentlyaeo.com/election-2026

Free to quote and screenshot with this credit and a link.

This tracker shows what AI assistants say when asked the same neutral questions every day. It is not a poll, a forecast or an endorsement. AI answers can be wrong or out of date, and poll numbers are reported as the AI stated them. Candidate photos are from Wikimedia Commons under their stated licences. Party icons: Font Awesome Free (CC BY 4.0).