TOTAL VOLUME:
$117.1b
24H VOL:
$122,493,166
24H TRANSACTIONS:
1,380,975,298
OPEN INTEREST:
$1,191,792,202
340,492
Markets across
34,140
events
MATCHED EVENTS:
4,396
PLATFORM COVERAGE:
5
Polymarket:
42%
VS.
Kalshi:
58%
At least 50%
all
2 markets
Kalshi
100%
Polymarket
72.8%
consensus
86.4%
spread
72.8-100%
(27.2pp)
News
Positive
Negative
Neutral
Hover marker for details
Aug 20
Aug 21
Aug 23
Aug 24
Aug 25
Aug 26
Aug 27
Vol.
$7.7k
·
Resolves Dec 31, 2026
$
Trade on Kalshi
Join Kalshi and score $25 for your first trade.At 100¢ buys you 100 shares | Odds: 99% Total Payout: $100 | Net Profit: $0 Multiplier: 1.00x | ROI: 0% | APY: 0% Illiquid market 125 days to resolutionTrade on Polymarket
At 72.8¢ buys you 137 shares | Odds: 72% Total Payout: $137 | Net Profit: $37 Multiplier: 1.37x | ROI: 37% | APY: 151% 126 days to resolutionThis event group tracks whether any Google Gemini model will achieve specific accuracy thresholds on Humanity's Last Exam by December 31, 2026. The markets are focused on determining if the model's performance meets or exceeds various percentage benchmarks.
This market will resolve to "Yes" if any Google Gemini model achieves at least the specified accuracy on Humanity’s Last Exam by December 31, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No". For resolution, “accuracy” refers solely to the value labeled “HLE Accuracy” or a clear equivalent metric if the data’s presentation or terminology is restructured, regardless of the model’s Calibration Error or any other displayed metric. The resolution source will be the official Humanity’s Last Exam leaderboard at https://agi.safe.ai/. If the resolution source becomes unavailable during the listed timeframe, this market will remain open to allow the relevant data to become available again. If the source remains unavailable after the end of the listed timeframe or is otherwise confirmed to be permanently unavailable, official Humanity’s Last Exam results published elsewhere may be used. If no official alternative source is available, this market will resolve to "No".
Resolution is determined by whether any language model achieves accuracy at or above specified thresholds on Humanity's Last Exam before December 31, 2026. The event contains nine separate markets corresponding to accuracy levels of 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, and 90%. Each market resolves independently to Yes if any language model reaches or exceeds its designated accuracy threshold on the exam during the specified timeframe. The determination is based on publicly reported results from the exam administrators or credible third-party verification of model performance.
On Polymarket, traders currently assign a 71.7% probability to the leading outcome, reflecting a strong consensus that Gemini will hit key benchmarks. This contrasts with many traditional analyst forecasts, which often remain more cautious due to differing methodologies and risk assumptions. The gap can provide early signals of market sentiment diverging from institutional expectations, especially as new test results or model updates emerge. Monitoring this market lets you see where crowd wisdom stands against expert opinion.
On Kalshi, pricing dynamics can diverge from Polymarket due to differences in user bases, liquidity, and market design. Polymarket and Kalshi can show different implied probabilities for the same outcome because of liquidity, fee structure, participant mix, and how each venue defines the contract. For example, Polymarket currently favors Will the highest score achieved by a Google Gemini model on Humanity’s Last Exam in 2026 be 50% or higher? at 71.7%, while Kalshi leans toward Will any LLM score at least 50% on Humanity's Last Exam before Dec 31, 2026? at 99.0%. Factors such as varying trader sentiment, regional participation patterns, and distinct order-book depths can all contribute to the spread of 27.3 between the two venues, creating opportunities for arbitrage or insight into shifting expectations.
This market resolves around Dec 31, 2026, with the outcome confirmed once the event is verifiable from credible public reporting. The final result will depend on official announcements or widely accepted test results showing the highest Gemini score achieved on Humanity’s Last Exam during 2026. As long as the data appears in reputable sources, the market will close and payouts will follow based on the recorded performance.
Key events such as major Gemini model updates, published test results from independent researchers, and announcements about new benchmark versions could all shift this market. High-impact signals include surprise performance leaks, regulatory comments affecting AI testing, or competing models posting strong scores that raise the bar. Traders will also watch for shifts in Polymarket and Kalshi odds, as changing sentiment on either venue often precedes broader market movements.