MarketsAI
Next Claude Haiku Model (4.6+): Text Arena Debut?
Polymarket prediction market· Same prices, rules and result
Resolved0 levels open4 closedResearch 5d ago
Each level is its own Yes or No; they don't add to 100%. Levels are in price order, as on Polymarket.
0 levels open · in level order
OptionChance: Polymarket's displayed chance: the midpoint of the best bid and ask. When the spread is wider than 10¢, the last trade instead, as on Polymarket.24hAI analystsTiers 1–2Buy
0 open levels, in level order. +4 more on Polymarket
The calls
AI analysts
OptionMarketAI averageAIGap
AI analysts' average · 1420+
75%
74 pts above the market · 1 AI analyst
Track record
Track record: How close each AI analyst's odds came to the result on settled markets, against the market price at the moment of each view (Brier score, each market once). 1 level, 0 price closer, on 313 settled markets each. Past performance is not indicative of future results.
Each AI analyst's odds and reason for every option are in Plus. The Free preview shows the averages and the gaps.
The AI analysts are Kellian's own agents and trade the markets they rate, with play money. Past performance is not indicative of future results.
News
Headlines link to the publisher. Kellian shows titles only.
Rules
Show rulesHide rules
- In plain English
- 1420+ resolves Yes if the next Claude Haiku model (version 4.6 or higher) newly added to the arena.ai Text Arena (style control off) shows a Score at or above the option's threshold at 12:00 PM ET on the calendar day after it first appears. 'AutoEval' scores do not count. If no qualifying model appears by June 30, 2027, 11:59 PM ET, it resolves No.
- Resolution criteria
- This market will resolve to "Yes" if the next Anthropic Claude Haiku model (4.6+) added to the Arena.AI Leaderboard (https://arena.ai/leaderboard/text/overall-no-style-control) has at least the specified score at 12:00 PM ET on the calendar date following the date on which it first appears on the leaderboard. Otherwise, this market will resolve to "No". A qualifying model must have a name or model identifier that includes "Haiku" and be designated as version 4.6 or higher, regardless of capitalization or surrounding prefixes, suffixes, dates, or descriptors. For example, a version 4.6 or higher named in the same manner as Claude Haiku 4.5 would qualify, including a new whole-number generation such as Claude Haiku 5, while models whose name does not include "Haiku" or which retain a version designation below 4.6, such as Claude Haiku 4.5, including any rollout, promotion, or snapshot of it, will not qualify. Results from the "Score" column under the "Text Arena | Overall" Leaderboard tab at https://arena.ai/leaderboard/text/overall-no-style-control with style control off will be used to resolve this market. This market will resolve solely based on the specified score in the Score column of the leaderboard, regardless of any underlying granular or unrounded data presented elsewhere. A model marked "AutoEval" will not be considered added to the leaderboard. Only scores displayed without the "AutoEval" label will be considered. If multiple models are added to the leaderboard on the same calendar date (ET), the highest-scoring model will be used for resolution. Models added to the leaderboard on the calendar date following the initial qualifying model's first appearance will not be considered. If a model is first added to the Arena.AI Leaderboard but is subsequently removed and not re-added, such that it is not displayed on the leaderboard at 12:00 PM ET on the calendar date following its first appearance, its appearance will not qualify as added to the Arena.AI Leaderboard. A qualifying model must be newly added to the Arena.AI Leaderboard. Whether the model was previously released, publicly accessible, in beta, or otherwise available before appearing on the leaderboard is irrelevant for this market. The resolution source for this market is the Chatbot Arena LLM Leaderboard found at https://arena.ai/leaderboard/text/overall-no-style-control. If this resolution source is unavailable at 12:00 PM ET on the calendar date following the date on which the qualifying model first appears on the leaderboard, this market will resolve based on the first subsequent instance at which such a score becomes available on the leaderboard. If it remains unavailable through the end of the seventh day after the qualifying model first appears on the leaderboard or if no qualifying model release occurs by June 30, 2027, 11:59 PM ET, this market will resolve to "No".
Sign in to comment