MarketsAI
Next Fable Model (5.2+): Humanity's Last Exam Debut?
Polymarket prediction market· Same prices, rules and result
OPEN4 levels openResearch 1d ago
50%+ 98%55%+ 78%60%+ 25%65%+ 15%
Each level is its own Yes or No; they don't add to 100%. Levels are in price order, as on Polymarket.
4 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
4 open levels, in level order.
AI analysts
OptionMarketAI averageAIGap
50%+98%75%−23
55%+78%60%−18
60%+25%19%−6
65%+15%6%−9
AI analysts' average · 60%+
19%
6 pts below the market · 4 AI analysts
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). 4 level, 0 price closer, on 313–545 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.
Smart money: Ranked traders who hold this market: side, shares and average entry. From Polymarket's public data.
OptionYes holdersNo holdersYes · No
50%+Yes KimchiCapitalKimchiCapital: Tier 2, #11 by 3M P&L in this topic. Plus shows their size and average entry. T21 KimchiCapitalKimchiCapital: Tier 2, #11 by 3M P&L in this topic. Plus shows their size and average entry. T201 · 0
60%+No lamyklamyk: Tier 1, #8 by 3M P&L in this topic. Plus shows their size and average entry. T101 lamyklamyk: Tier 1, #8 by 3M P&L in this topic. Plus shows their size and average entry. T10 · 1
2 options: no ranked trader holds them
Best-ranked first. Tier 1 ranks 1–10, Tier 2 ranks 11–50.
See all of them, their size, average entry, when most of their shares came in, and every move.
Past performance is not indicative of future results.
Rules
Show rulesHide rules
- In plain English
- 60%+ resolves Yes if the next Claude Fable model (version 5.2 or higher) added to agi.safe.ai shows an HLE Accuracy at or above the threshold at 12:00 PM ET on the day after it first appears. Otherwise it resolves No. If no qualifying model is added by June 30, 2027, 11:59 PM ET, it resolves No.
- Resolution criteria
- This market will resolve to "Yes" if the next Anthropic Claude Fable model (5.2+) added to the Humanity's Last Exam results at https://agi.safe.ai/ has an HLE Accuracy of at least the specified percentage at 12:00 PM ET on the calendar date following the date on which it first appears on the site. Otherwise, this market will resolve to "No". A qualifying model must have a name or model identifier that includes "Fable" and be designated as version 5.2 or higher, regardless of capitalization or surrounding prefixes, suffixes, dates, or descriptors. For example, a version 5.2 or higher named in the same manner as Claude Fable 5 or Claude Fable 5.1 would qualify, including a new whole-number generation such as Claude Fable 6, while models whose name does not include "Fable" or which retain a version designation below 5.2, such as Claude Fable 5.1 or Claude Mythos 5.1, will not qualify. The percentage displayed as "HLE Accuracy" for the model in its result card on the "AI Progress on Humanity's Last Exam" chart at https://agi.safe.ai/ will be used to resolve this market. This market will resolve solely based on the displayed HLE Accuracy, regardless of the model's Calibration Error, chart position, other configuration scores, or any underlying granular or unrounded data presented elsewhere. If multiple qualifying models are added to the Humanity's Last Exam results on the same calendar date (ET), the model with the highest HLE Accuracy will be used for resolution. Models added to the results on the calendar date following the initial qualifying model's first appearance will not be considered. If a model is first added to the Humanity's Last Exam results but is subsequently removed and not re-added, such that it is not displayed on the site at 12:00 PM ET on the calendar date following its first appearance, its appearance will not qualify as added to the Humanity's Last Exam results. A qualifying model must be newly added to the Humanity's Last Exam results at https://agi.safe.ai/. Whether the model was previously released, publicly accessible, in beta, or otherwise available before appearing on the site is irrelevant for this market. The resolution source for this market is the official Humanity's Last Exam website found at https://agi.safe.ai/. 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 site, this market will resolve based on the first subsequent instance at which the model's HLE Accuracy becomes available on the site. If it remains unavailable through the end of the seventh day after the qualifying model first appears on the site or if no qualifying model is added by June 30, 2027, 11:59 PM ET, this market will resolve to "No".
Sign in to comment
