TOTAL VOLUME:

$134.1b

24H VOL:

$141,541,542

24H TRANSACTIONS:

2,388,728,490

OPEN INTEREST:

$1,440,096,988

406,065

Markets across

30,522

events

MATCHED EVENTS:

2,692

PLATFORM COVERAGE:

5

Polymarket:

39%

VS.

Kalshi:

61%

BETA
Dashboards
Insights
Indices
Tour
All
Trending
Breaking
New
Ending Soon
Politics
Sports
Crypto
Companies
Elections
Financials
Economics
Other
Entertainment
Science and Technology
Highest score on Humanity’s Last Exam in 2026?
kalshi
polymarket

Highest score on Humanity’s Last Exam in 2026?

Total volume:
$136,005
Volume 24h:
$2,005
41%
Liquidity:
$5,267
47%
Open interest:
$23,395
0.2%

At least 50%

 - Kalshi

At least 50% - Kalshi

1W

News

Positive

Negative

Neutral

Hover marker for details

Vol.

·

Resolves Jan 1, 2027

Will any LLM score at least 50% on Humanity's Last Exam before Dec 31, 2026?

99%chance
Amount

$

Trade on
kalshi

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 92 days to resolution
You will be redirected to the platform to complete this trade.
Outcome
Trade
Chance %
Price
Spread
Liquidity
Volume
24h
7d
Open Interest
Ends in
Result
kalshi

At least 50%

Trade
99%
Yes 100¢No 3¢
3¢
N/A
$3,137
0%
0%
$2,653
3mo 2d
active
kalshi

At least 55%

Trade
98%
Yes 98¢No 8¢
6¢
N/A
$6,702
0%
0.28%
$6,107
3mo 2d
active
kalshi

At least 80%

Trade
53%
Yes 10¢No 96¢
6¢
N/A
$1,562
0%
2%
$940
3mo 2d
active
polymarket

80%+

Trade
7%
Yes 7.3¢No 93.4¢
0.7¢
$646
$1,710
0%
0%
N/A
3mo 3d
active
PredictionHero
Market Consensus
30%
Yes 8.6¢No 94.7¢
Avg: 3.4¢Max: 6¢
kalshi

At least 60%

Trade
51%
2%
Yes 54¢No 49¢
3¢
N/A
$11,770
2%
7%
$4,392
3mo 2d
active
polymarket

60%+

Trade
50%
7%
Yes 50¢No 51¢
1¢
$994
$52,454
2%
15%
N/A
3mo 3d
active
PredictionHero
Market Consensus
50.5%
Yes 52¢No 50¢
Avg: 2¢Max: 3¢
kalshi

At least 65%

Trade
43%
11%
Yes 39¢No 64¢
3¢
N/A
$8,838
0.58%
27%
$3,551
3mo 2d
active
polymarket

65%+

Trade
34%
Yes 35¢No 67¢
2¢
$959
$26,423
2%
59%
N/A
3mo 3d
active
PredictionHero
Market Consensus
38.5%
Yes 37¢No 65.5¢
Avg: 2.5¢Max: 3¢
kalshi

At least 70%

Trade
21%
Yes 23¢No 83¢
6¢
N/A
$6,080
0%
30%
$2,947
3mo 2d
active
polymarket

70%+

Trade
14%
2%
Yes 15¢No 87¢
2¢
$643
$7,566
0.49%
17%
N/A
3mo 3d
active
PredictionHero
Market Consensus
17.5%
Yes 19¢No 85¢
Avg: 4¢Max: 6¢
kalshi

At least 75%

Trade
14%
Yes 16¢No 91¢
7¢
N/A
$1,405
0%
6%
$910
3mo 2d
active
polymarket

75%+

Trade
12%
Yes 12¢No 89¢
1¢
$1,075
$3,746
0%
2%
N/A
3mo 3d
active
PredictionHero
Market Consensus
13%
Yes 14¢No 90¢
Avg: 4¢Max: 7¢
kalshi

At least 90%

Trade
9%
Yes 5¢No 99¢
4¢
N/A
$1,286
0%
0%
$1,260
3mo 2d
active
polymarket

90%+

Trade
5%
Yes 5.7¢No 94.9¢
0.6¢
$950
$2,485
0%
0.81%
N/A
3mo 3d
active
PredictionHero
Market Consensus
7%
Yes 5.4¢No 97¢
Avg: 2.3¢Max: 4¢
kalshi

At least 85%

Trade
4%
Yes 8¢No 98¢
6¢
N/A
$840
0%
0%
$635
3mo 2d
active
Total markets: 15

Description

This group of markets centers around the performance of language models on the Humanity's Last Exam (HLE) in 2026. The markets aim to predict whether a language model will achieve a certain accuracy score on this exam, with scores ranging from 50% to 90% being considered.

PredictionHero - Resolution Divergence Alerts (RDA)

Divergence Detected

Issue: The markets diverge in their specific questions and thresholds. Kalshi offers multiple markets for different accuracy levels, while Polymarket focuses on specific thresholds in individual markets.Hero tip: Analyze the probabilities across both platforms to understand market sentiment regarding different accuracy levels. Focus on the highest probability thresholds on Kalshi as indicators for Polymarket's markets.

Critical divergence points:

  • Polymarket: Focuses on specific accuracy thresholds (60%, 65%, 70%, 75%, 80%, 90%) in individual markets. Resolves 'Yes' if any model achieves at least that threshold. "This market will resolve to "Yes" if any model achieves at least the specified accuracy on Humanity’s Last Exam by December 31, 2026, 11:59 PM ET."
  • Kalshi: Lists multiple accuracy thresholds (50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%) as independent markets. Each market resolves 'Yes' if any model achieves that specific threshold. "If any language model achieves an accuracy of at least 50% on Humanity's Last Exam before Dec 31, 2026, then the market resolves to Yes."
Our PredictionHero Resolution Divergence Alerts (RDA) are there to help users identify potential differences across platforms. They do not replace or supersede the official rules and description of any prediction market. Users are solely responsible for reviewing and understanding the applicable rules and resolution criteria before placing any trade or bet. If you notice a potential inconsistency, discrepancy, or error in an alert, please report it to our team so we can review and improve the accuracy of our data.

Polymarket

This market will resolve to "Yes" if any 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".

Kalshi

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.

Frequently asked questions

On Polymarket and Kalshi, the Humanity’s Last Exam market dashboard aggregates trading activity from multiple platforms to provide a consensus view of the likely highest score achieved on the exam in 2026. Currently, total volume across these platforms is $136,005, with $2,005 traded in the last 24 hours. Polymarket currently favors Will the highest score achieved on Humanity’s Last Exam in 2026 be 60% or higher? at 49.5%, while Kalshi leans toward Will any LLM score at least 50% on Humanity's Last Exam before Dec 31, 2026? at 99.0%. This allows traders to see a combined probability and overall market interest in the Humanity’s Last Exam market.

Prediction market odds, like those found in this market, often reflect a 'wisdom of the crowd' that can differ from individual analyst forecasts. Analysts may be subject to biases or have limited access to all relevant information, whereas a prediction market aggregates the opinions of many participants with financial incentives to be accurate. While analyst predictions can provide valuable insights, the collective forecasting power of this market can offer a distinct perspective on the potential outcomes of the Humanity’s Last Exam. It's important to consider both sources of information when forming your own view.

Prices on Polymarket and Kalshi can diverge due to several factors. Different user bases, trading fees, and market-specific rules can all contribute to price discrepancies. 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. Furthermore, liquidity can vary between the platforms, meaning that a large trade on one platform might have a greater price impact than on another. The differing leading outcomes—Will the highest score achieved on Humanity’s Last Exam in 2026 be 60% or higher? on Polymarket at 49.5% and Will any LLM score at least 50% on Humanity's Last Exam before Dec 31, 2026? on Kalshi at 99.0%—also demonstrate differing interpretations of the exam's potential results. This creates arbitrage opportunities for traders.

This market resolves around Jan 1, 2027, with the outcome confirmed once the event is verifiable from credible public reporting. The highest score achieved on the Humanity’s Last Exam in 2026 will be determined by publicly available results released by the exam administrators. The market will settle based on this verified score, representing the collective prediction of traders regarding the exam's difficulty and the capabilities of those taking it. Trading will cease prior to this date, allowing for a clear determination of the winning outcome.

Several signals could significantly impact this market. Major advancements in artificial intelligence, particularly in large language models, could shift expectations about exam performance. Public statements from the exam creators regarding the exam's difficulty or format could also influence trading activity. Unexpected changes in educational trends or the availability of study resources could also play a role. Finally, any news regarding the exam's administration or scoring procedures would likely cause movement in the market, as traders adjust their predictions based on new information.