Which company has the best Math AI model end of July?

Platform comparison

Market context

Anthropic currently holds the top spot in the Chatbot Arena’s Text Arena | Math leaderboard, with claude-opus-4-6-thinking ranked first at 1518 Elo as of July 2026[3]. OpenAI’s gpt-5.4-high sits just behind at second place in math, while Google’s gemini-3.1-pro-preview trails at third[1]. The 49% crowd-implied probability reflects a tight contest where Anthropic leads but faces credible pressure from OpenAI, whose models have historically closed gaps quickly in arena rankings.

Historical trends show math Elo has risen by +172 points since tracking began, averaging 10.4 points per month, making it one of the fastest-improving categories in LLM performance[3]. Past leaderboard shifts often hinge on model updates released in the final quarter before settlement; for example, claude-fable-5 overtook coding leaders after a mid-2025 release, altering the top rank within weeks[3]. This pattern suggests the current lead is not guaranteed, especially if OpenAI or Google announce a math-focused upgrade before July 2026.

Traders should monitor release calendars for Anthropic, OpenAI, and Google, particularly any announcements of “thinking” or “reasoning” variants targeting math tasks. A recent Swfte AI report notes Anthropic’s Claude Fable 5 leads a composite quality index across 362+ models, but that ranking blends price and speed, not pure math Elo[2]. The decisive factor will be the live leaderboard check on 31 July 2026 at 12:00 PM ET, where style control is off and rank is determined solely by arena votes[1]. Any new model launch in the next six months could reset the hierarchy.

Sources: 1 · 2 · 3 · 4 · 5

Methodology

Sports-specific comparison page for Which company has the best Math AI model end of July?. Polymarket's live quote (Polygon order book) plus platform attributes for the three reference venues. Sports markets reward liquidity — Polymarket and Betfair are materially deeper than Kalshi or Manifold.

Resolution & payout

Sports markets typically settle on official final-whistle plus league confirmation. Polymarket uses UMA Optimistic Oracle with a source URL per contract — usually official league data feeds or ESPN/Soccerway. Two-hour dispute window, then smart-contract payout in USDC.

FAQ

When do sports markets resolve?

Typically within hours of the official final whistle. Polymarket uses UMA Optimistic Oracle with source URLs pointing at official league data feeds — e.g. the Premier League for EPL markets, UEFA for Champions League, FIFA for World Cup.

What are live sports odds on Polymarket?

Some top-tier matches stay open during play — you can trade the half-time probability in the 70th minute. Polymarket mid-prices update second-by-second; any frontend mirroring the order book shows the same movement.

Which sports markets are available?

Football (soccer) dominates — Champions League, World Cup, Premier League, La Liga, Bundesliga — followed by NFL, NBA, tennis Grand Slams, Formula 1, boxing/MMA. Resolution via official league source confirmation.

How fast do sports winnings settle?

Once the official league outcome is logged in the UMA Oracle (typically 1-2 hours after the final whistle), Polymarket's smart contract triggers USDC payout. To your wallet within minutes.

What's the difference between match odds and outright odds?

Match odds cover a single game ("Bayern beats BVB"). Outright odds are long-term aggregates ("Bayern wins the league"). Outright markets have deeper liquidity; match markets have faster resolution.