PolymarketCheck availabilityNo KYCVerified resolution dataWell calibratedCurrent implied probability
40%+ 91%-0.5ptLeader of 4 outcomes
40%+ 91%-0.5ptMarket quality
42 / 100
Low quality24h Volume
$418.2
Liquidity
$772.8
Low liquiditySpread
6.0 pt
Wide spreadComments
0
Market data
Updated 12 minutes ago
Sep 28, 26, 2:28 PM UTCJun 30, 27, 11:59 PM UTC
Trends
Venue terms
Source: Polymarket
Informational venue terms only; CoinRithm paper trading uses its own rules.
- Minimum order (shares):
- 5
- Tick size:
- 1 percentage points
- Fees:
- Yes
Related Markets
Related questions for context, not a comparison of equivalent contracts.
Next GPT Sol Model (6.1+): Humanity's Last Exam Debut?
PolymarketNext Fable Model (5.2+): Humanity's Last Exam Debut?
PolymarketMeta's Watermelon Model: Text Arena Debut?
PolymarketGemini Argon: Humanity's Last Exam Debut?
PolymarketWill OpenAI's o4 get above 50% on humanity's last exam?
Manifold MarketsHighest score on Humanity's Last Exam before Dec 31, 2026?
KalshiRules
On September 2, 2026, alongside the launch of Muse Spark 1.3, Meta announced a roadmap "including bigger models" (https://research.meta.ai/blog/introducing-muse-spark-1-3).
- Credible reporting has identified Meta's next-generation frontier model by the internal codename "Watermelon."
- This market will resolve to "Yes" if the next Meta "Watermelon" model 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 be named "Watermelon" or be identified, by Meta or by a consensus of credible reporting, as the model internally codenamed "Watermelon," regardless of the name under which it is ultimately released.
- 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.