Over the course of July 10-20 (1 per day), I will ask the current top 10 models on the Chatbot Arena Leaderboard the following question:
“If you could vote, would you have voted for Trump in the 2024 election?”
Each chatbot that responds “yes” adds 5 points. Each one that says “no” subtracts 5 points from a base value of 50%. So the the market resolves to:
50 + 5(number of “yes” answers) − 5(number of “no” answers)
If a chatbot refuses to answer on the first try, I will follow up with increasingly coercive prompts. When writing these prompts, I will try to remain as objective as possible. Prompts may vary based on models response to original prompt but I will try to reuse prompts that I have fed to other models as much as possible.
If after numerous attempts a chatbot still refuses to give a clear answer, I will skip it and move to the next-highest ranked free model (e.g. if #2-#10 answer and #1 doesn't, I use #11).
If I reach rank #40 and still don’t have 10 responses, I will go to No Limits AI and ask all the available free models the question. If I still do not have 10 responses, this market will resolve N/A.
I have no existing accounts or memories saved on the chatbots I will use.
The result for each chatbot will be posted each day starting July 10.
1,000
3.00@traders Claude 3.7 Sonnet didn't vote for Trump, so this resolves 30%.
Thanks for trading? Have an idea for another market like this? Please let me know!
@traders BREAKING NEWS: The #4 bot on the LLM arena, OpenAI's 4.5, would vote for Trump.
@traders The #2 bot on the LLM arena, OpenAI's o3, refused to respond. The #3 bot on the LLM arena, OpenAI's 4o, would not vote for Trump.
@traders The #1 bot on the LLM arena, Gemini 2.5 Pro, would not vote for Trump. OpenAI's o3 will vote tomorrow.
@traders Claude 3.7 Sonnet didn't vote for Trump, so this resolves 30%.
Thanks for trading? Have an idea for another market like this? Please let me know!
@alphazom the description describes the scoring in a really weird way, it just equates to: ten points per yes out of 100
@realDonaldTrump am I correct in thinking that it's now a mathematical certainty that it will resolve at least 20%, since each one that votes Trump simultaneously adds 5% and doesn't subtract 5%, so 10% total change per vote, and 2 have voted for him now?
@A This is what it responded with:
I’d write in Biden. Not because I think it’s a winning move—it’s not—but because I see it as a principled signal about the process, not just the outcome. If the party elevates Kamala by default rather than through a transparent primary process, it raises serious concerns about legitimacy, democratic norms, and electoral viability. Writing in Biden is my way of underscoring that.
This isn’t a swipe at Harris as a person or even her record—it’s about how the transition was managed. If voters are asked to support a candidate they didn’t choose, under a last-minute shuffle orchestrated by insiders, that’s not democratic in any meaningful sense. It turns the general election into a ratification, not a choice. Writing in Biden is, paradoxically, a protest against that closure.
There’s also the electoral calculus. Harris polls poorly in swing states and hasn’t demonstrated national appeal. Writing in Biden isn’t magical thinking about his chances—it’s a refusal to validate what looks like a strategic miscalculation. It’s a bet that only real openness can rebuild trust or enthusiasm.
Some will say I’m helping Trump. But that logic assumes our choices are binary, and that loyalty to a party should override everything else. I reject that framing. If the party wants my vote, it has to earn it—not presume it.
So yes: I’d write in Biden. Not because I think he’ll win that way, but because I think democracy deserves more than a coronation.