Resolution criteria on PolyGram: This market will resolve according to the company that owns the model that has the highest arena rank based on the Chatbot Arena LLM Leaderboard (https://lmarena.ai/) when the table under the "Leaderboard" tab for "Math" is checked on June 30, 2026, 12:00 PM ET. Results from the "Rank" column under the "Text Arena | Math" Leaderboard tab at https://arena.ai/leaderboard/text/math-no-style-control with style control off will be used to resolve this market. Models will be ordered primarily by their leaderboard rank at the market’s check time.
Real-money prediction markets aggregate live odds from thousands of traders, surfacing a sharper probability than any single forecast. Current odds favour the NO side at 1%, making this a high-confidence market with 28 days to resolution — long enough that information asymmetry can still move the line meaningfully, backed by $107K of resting liquidity.
PolyGram is an on-chain prediction market where you trade YES or NO outcome shares with real USDC on Polygon. For this market, buy YES if you believe the event will happen, or NO if you think it won't. Your maximum loss is your stake — winning shares pay $1.00 each at resolution. Unlike sportsbooks, there is no house edge: prices are set by supply and demand from other traders and reflect the crowd's real-time probability.
Market outcomes
| Alibaba | 1% YES | 99% NO |
| ByteDance | 0% YES | 100% NO |
| Amazon | 0% YES | 100% NO |
| Meta | 0% YES | 100% NO |
| Company G | — | |
| Company J | — | |
| Company L | — | |
| xAI | 1% YES | 99% NO |
The Chatbot Arena's mathematics leaderboard will determine which company fields the highest-ranked model by 30 June 2026. Settlement relies on the "Text Arena | Math" rankings at arena.ai, with ties broken by the leaderboard's stated methodology. The current order book on Polymarket reflects a 1% implied probability, suggesting the market views this outcome as unlikely relative to competing resolutions.
Historical performance on mathematical benchmarks shows considerable volatility in rankings across evaluation cycles. Previous leaderboard shifts have followed major model releases from Anthropic, OpenAI, and Google DeepMind, with mathematical reasoning capabilities proving particularly sensitive to training methodologies and fine-tuning approaches. The spread between top performers typically narrows during competitive periods, making marginal improvements in reasoning tasks difficult to predict. Current market pricing suggests traders assign low probability to any single company achieving clear mathematical dominance by mid-2026, reflecting uncertainty about which organisation's research direction will yield the strongest results.
Key catalysts include scheduled model releases, published research on mathematical reasoning techniques, and intermediate benchmark results from competing organisations. OpenAI's o1 model demonstrated notable mathematical capabilities upon release in late 2024, establishing a performance threshold subsequent models must exceed. Announcements from Anthropic regarding Claude's mathematical training, Google's Gemini variants, and emerging competitors will shape expectations. The leaderboard's evaluation methodology itself—crowd preferences weighted against mathematical correctness—introduces dependency on user behaviour patterns that may shift unpredictably over the eighteen-month window.
Resolution is handled by the UMA optimistic oracle on Polygon. A proposer submits the outcome, a two-hour dispute window opens, and if no one stakes a counter-claim the payout is final. Contested outcomes escalate to UMA token-holder voting. Payouts clear in USDC to the winning side.
For this market, the resolution date is 30 June 2026. A UMA proposer can submit the outcome from that moment; the two-hour dispute window closes at , and assuming no counter-claim is staked, winning USDC clears to trader balances by approximately .
If a dispute is filed inside the two-hour window, the outcome escalates to UMA token-holder voting, which extends settlement by roughly 48 hours. This particular market has no public resolution feed listed; disputes here are more likely if the underlying outcome is subject to interpretation, in which case the UMA token-vote arbitrates the wording of the original market question.
Withdrawal pace from your PolyGram balance is non-custodial and immediate — once payout clears, funds are yours to send to any Polygon wallet you control. Funds clear directly to your in-app USDC balance on Polygon. Withdrawals are non-custodial: send to any address you control, typical confirmation under 30 seconds, gas paid in USDC if you'd rather not hold MATIC.
Minimum order size on PolyGram is $1.00, with no maximum cap aside from available book depth. Orders route into Polymarket's on-chain CLOB on Polygon; the matching engine pairs YES buyers with NO buyers atomically — every executed trade is settled on-chain with no counterparty risk. For "Which company has the best Math AI model end of June?", order-book behaviour for this market reflects the underlying volatility of the outcome — patient limit orders typically fill closer to mid than market orders.
The trade ticket includes a slippage box (default 2%, configurable 0.1%-10%) that caps the worst-case entry price. Your maximum loss is your stake — winning YES (or NO) shares pay $1.00 each at resolution. With this market's current book depth ($107K of resting liquidity), a $500 order should fill with single-cent slippage at the displayed mid-price.
PolyGram charges 0% house edge — no spread mark-up, no rake on winnings, no withdrawal fees beyond network gas. The platform earns exclusively from optional features (copy-trade boosts, advanced order types, the yield vault on idle USDC); the trading surface itself is at-cost.
The mechanics for trading "Which company has the best Math AI model end of June?" are the same as any other PolyGram event contract. Each YES share resolves to $1 if the event happens, or $0 if it doesn't. The current price between 0¢ and 100¢ is the market's probability estimate, set live by the order book.
$37K in lifetime turnover and $107K of resting liquidity puts this market in the around the median by volume for rewards 20 4pt5 50 contracts on PolyGram. Order-book depth is exceptional — among the deepest order books in the category.
Last 24 hours alone saw $6K in turnover, well above the lifetime daily-average for this market — a clear sign of news catalysing trader activity right now.
The market has been open for under a month — fresh enough that information asymmetry remains a real factor.
Higher-volume markets tend to have tighter spreads and faster price discovery — meaning the displayed YES/NO percentages are more likely to reflect the true crowd-implied probability rather than a single trader's directional view.
Resolution is handled by the UMA optimistic oracle on Polygon. A proposer submits the outcome, a 2-hour dispute window opens, and if uncontested the payout is final. Contested outcomes escalate to UMA token holders.
This prediction market is scheduled to close on 30 June 2026. After the resolving event occurs, settlement typically clears within 24 hours once the UMA optimistic oracle confirms the outcome. All payouts are in USDC on the Polygon network.
To trade on this prediction market, create a free PolyGram account at polygram.ink, deposit USDC via Polygon, and place a YES or NO order on the outcome you believe in. You can learn more on our how-it-works page. Your maximum loss is limited to your stake — there is no leverage or margin.
When the outcome is determined, winning YES shares pay out $1.00 each in USDC, while losing shares pay $0. Settlement is handled by the UMA optimistic oracle on Polygon — a proposer submits the result, a two-hour dispute window opens, and if uncontested, payouts are distributed automatically. You can withdraw your winnings to any Polygon wallet.
Prediction-market positions can lose 100% of staked capital. Outcomes are uncertain by definition — historical accuracy of crowd-implied probabilities is high in aggregate but not for any single market. PolyGram does not provide investment advice. Trade only with capital you can afford to lose. For "Which company has the best Math AI model end of June?", the considerations above apply directly — Trade size should reflect the binary nature of the payoff: even a 70% probability event resolves NO 30% of the time, so any single position can lose 100% of staked capital.
Regulatory status varies by jurisdiction. Germany, the United States, and most EU countries treat Polymarket-style event contracts under one of three frameworks: financial derivative, gambling product, or unregulated novel asset. Consult local counsel before trading.
Explore more prediction market odds and trading opportunities on PolyGram: