Will any AI model reach ___ Coding Arena Score by December 31?: how this market works

What you need to know

This market asks whether any AI model will become good enough at coding, as measured by a specific public scoreboard, to hit a numerical target by the end of 2026. The scoreboard is called Chatbot Arena, and it ranks AI models based on how often real users prefer one model over another in head-to-head coding tasks. A higher score means users consistently pick that model over its competitors. There are three separate versions of this market, one each for scores of 1560, 1580, and 1600, with different odds for each threshold. Each version resolves Yes if any AI model's score in the coding category on the Arena.ai leaderboard, with style control turned off, reaches or passes the target number before December 31, 2026 at 11:59 PM Eastern Time. The score must appear in the official Score column on that specific leaderboard tab. If the website is down when someone checks, the market stays open until it comes back. If the site goes offline permanently, all three markets resolve No, which is worth knowing as an edge case. None of the provided news headlines are related to this market. They cover unrelated topics like poetry, land policy, immigration, and local business awards. The kind of news that would actually matter here is a major AI lab releasing a new coding model, or any model's Arena score crossing one of the three thresholds on the official leaderboard. AI capabilities are improving fast but not on a perfectly predictable schedule. The 1560 threshold is priced at 69%, suggesting the market finds it more likely than not to be reached. The 1580 and 1600 bars drop to 35% and 29%, reflecting how much harder each extra step becomes. A single strong model release could move all three markets at once. But Arena scores depend on user votes, not just raw model quality, so adoption and usage patterns also matter. Eighteen months is a long horizon in AI, which cuts both ways.

The odds right now

• 1560+32.0 pts (1w)69%
• 1580+5.0 pts (1w)35%
• 1600+19.0 pts (1w)29%

Price history

How this resolves

Resolves December 31, 2026

This market will resolve to "Yes" if any model on the Arena.AI Leaderboard (arena.ai/leaderboard/text) reaches at least the specified Arena Score on the "Leaderboard" tab for "Coding" by December 31, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No". Read the full resolution rules on the live market page.

Related

Same markets. A fraction of the fee.

These apps all route to the same exchange order book. The difference is what each one adds on top of the exchange's own fee.

Published rates, checked July 2026. MetaMask charges a flat 4 percent per prediction trade. Jupiter adds a fee equal to the exchange's own taker fee at fill time, roughly 2 to 4 percent at typical odds. Where a market carries an exchange settlement fee, it applies everywhere, whichever app you use. Paridesk adds nothing on maker orders.

Trade this market on Paridesk: non-custodial, 0.5% fee.