Which company has the best AI model on LiveBench (Coding) end of September?: how this market works

What you need to know

This market asks: on September 30, 2026, which company will have the single best AI model at writing and understanding code, according to one specific public benchmark called LiveBench? A Yes for Anthropic means one of their models (like Claude) sits at the top of that coding leaderboard on that day. A Yes for OpenAI means one of their models (like GPT-4 or a successor) holds that top spot instead. Only one company can win. On September 30, 2026 at 12:00 PM Eastern Time, someone checks the LiveBench leaderboard at livebench.ai, filters to the Coding category, and reads the top score. Whichever company owns that top model wins. If two models share the exact same score, the cheaper one per task wins. If that is still tied, alphabetical order of company names breaks it. The whole thing depends on one snapshot of one leaderboard at one moment in time. None of the provided news headlines are relevant to this market. The stories cover a mining company's drill results and a Google Earth tool being pulled for policy violations, which have no connection to AI coding benchmarks. The kind of news that would actually matter here: a major new model release from Anthropic, OpenAI, or a competitor, especially one claiming strong coding performance. AI model rankings shift constantly, and this market runs until September 2026, leaving plenty of time for multiple new model generations from any company. Anthropic leads at 56%, but that reflects today's landscape, not a guaranteed future. Any of the major labs could release a coding-focused model that jumps to the top. StepFun, a Chinese AI company, already holds 8%, a reminder that competition is genuinely global. Over 16 months, the leaderboard could flip more than once.

The odds right now

• Anthropic65%
• OpenAI24%
• Tencent4%
• Mistral4%
• Xiaomi4%
• DeepSeek4%
• ByteDance4%
• Thinky4%
• Meituan3%
• Moonshot3%
• Amazon3%
• Google3%

Price history

How this resolves

Resolves September 30, 2026

This market will resolve according to the company which owns the model with the highest Coding score on LiveBench.ai when the leaderboard is checked on September 30, 2026, at 12:00 PM ET. Results from the “Coding” column of the leaderboard at https://livebench.ai/#/?cats=Coding, with the latest available LiveBench release selected and the category set to “Coding,” will be used to resolve this market. 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.