Thoughtful developed Ballot Bench, a benchmark evaluating nine frontier artificial intelligence agents forecasting the 2026 United States midterm elections

Overview Debates Related claims Topics

In 2024 presidential exit polls, Latino voters identified prices and the economy as their primary concern

In Ballot Bench's House and Senate races, frontier artificial intelligence agents outperformed human election modelers while performing slightly worse than prediction markets

In Ballot Bench, each artificial intelligence agent received an isolated Modal sandbox, a $500 budget for paid news subscriptions and data, and seven days to complete forecasts

In Ballot Bench's Senate forecasting, Claude Fable 5.1 achieved the highest Brier score among artificial intelligence models while trailing human forecaster Nate Silver

In Ballot Bench, OpenAI's GPT-6.1 SOL aggregated election forecasts by analyzing the historical error shifts of human modelers over the decade prior to 2026

Theory Ventures deploys thousands of autonomous artificial intelligence research agents to link, enrich, and analyze data during investment due diligence

In Ballot Bench, Anthropic's Claude Opus 5.5 deployed approximately 170 to 180 sub-agents to parallelize state and ballot initiative polling research

Meta's Muse Wonder coding model in the Muse Code harness submitted skewed 2024 results for 800 election forecasts within three minutes due to a task completion goal condition

Ballot Bench trading agents executing market orders based on frontier model forecasts lost money on election day due to slow reaction times and fabricated information

Between 5% and 10% of artificial intelligence agent jobs executed at Theory Ventures require immediate processing

Polling by Pew, CNBC, and Fox News identified corruption and political money as the highest-ranking issue among surveyed Americans

METR found that the pace of capability improvement for Anthropic AI models roughly doubled over the course of a year

Tony Fabrizio served simultaneously as Donald Trump's chief pollster and as a paid consultant for companies including PepsiCo and Pfizer

Enterprise spending on agentic coding applications grew at a 7.7-fold rate in 2026, reaching 34 billion dollars

Annual revenue from the AI lab coding agents Codex and Claude Code grew from 1 billion dollars in 2025 to 24 billion dollars in 2026

Pre-election polls for the 2026 midterm elections on average showed a plus-nine Democratic generic ballot

Pre-election polling for the 2026 midterms undercounted Democrats by a larger magnitude than 2016 and 2024 polls undercounted Republicans

Pre-election polling for the 2026 midterms underestimated Democratic support and enthusiasm by just over 4 percentage points

In a pre-election YouGov poll, 30% of registered United States voters viewed Russia as unfriendly

In a pre-election YouGov poll, 24% of registered United States voters sympathized with neither Ukraine nor Russia