SimpleFunctions
Winner-take-all answer·16 source contracts·Kalshi 16·refreshed just now·Closes Dec 31, 2027 · 495d

Will any LLM score at least 60% on Humanity's Last Exam before Dec 31, 2027

Leader sits at 97% across 16 bound outcomes, runner-up at 88%. This is a winner-take-all market — the headline is the leader’s price, not an arithmetic mean.

Leader probability

97%

At least 50%

runner-up 88¢leader 97¢

Outcomes

16

winner-take-all

Runner-up

88¢

At least 55%

Spread

9pp

contested

24h volume

$227

thin orderbook

Closes

Dec 31, 2027

495 days

Venue

Kalshi

16 bound

30-day trend

0%50%100%-30d-3w-2w-1wtodayAt least 50%: 86% (30 days, 6 points)At least 50%: 86% on 2026-08-20At least 55%: 89% (30 days, 26 points)At least 55%: 89% on 2026-08-22At least 60%: 87% (30 days, 26 points)At least 60%: 87% on 2026-08-23
At least 50%86¢At least 55%89¢At least 60%87¢
Top 3 candidates by current price · 30d

Bracket family

How the bracket ladder is priced.

Each row is one outcome on the venue. Sorted by 24h volume — the heaviest book is at the top.

Cluster 1

Will any LLM score at least

16 contracts$227
OutcomePrice24hVolumeVenueDetail

Will any LLM score at least 60% on Humanity's Last Exam before Dec 31, 2026?: At least 60%

KXLASTEXAM-26DEC31-T60

60¢±0$217K

Will any LLM score at least 65% on Humanity's Last Exam before Dec 31, 2026?: At least 65%

KXLASTEXAM-26DEC31-T65

30¢1pp$10K

Will any LLM score at least 95% on Humanity's Last Exam before Dec 31, 2027?: At least 95%

KXLASTEXAM-27DEC31-T95

11¢+1pp$0K

Will any LLM score at least 90% on Humanity's Last Exam before Dec 31, 2027?: At least 90%

KXLASTEXAM-27DEC31-T90

18¢+1pp$0K

Will any LLM score at least 85% on Humanity's Last Exam before Dec 31, 2027?: At least 85%

KXLASTEXAM-27DEC31-T85

24¢±0$0K

Will any LLM score at least 80% on Humanity's Last Exam before Dec 31, 2027?: At least 80%

KXLASTEXAM-27DEC31-T80

38¢±0$0K

Will any LLM score at least 75% on Humanity's Last Exam before Dec 31, 2027?: At least 75%

KXLASTEXAM-27DEC31-T75

57¢±0$0K

Will any LLM score at least 70% on Humanity's Last Exam before Dec 31, 2027?: At least 70%

KXLASTEXAM-27DEC31-T70

61¢±0$0K

Will any LLM score at least 65% on Humanity's Last Exam before Dec 31, 2027?: At least 65%

KXLASTEXAM-27DEC31-T65

78¢±0$0K

Will any LLM score at least 60% on Humanity's Last Exam before Dec 31, 2027?: At least 60%

KXLASTEXAM-27DEC31-T60

86¢±0$0K

Will any LLM score at least 85% on Humanity's Last Exam before Dec 31, 2026?: At least 85%

KXLASTEXAM-26DEC31-T85

3¢±0$0K

Will any LLM score at least 80% on Humanity's Last Exam before Dec 31, 2026?: At least 80%

KXLASTEXAM-26DEC31-T80

6¢±0$0K

Will any LLM score at least 75% on Humanity's Last Exam before Dec 31, 2026?: At least 75%

KXLASTEXAM-26DEC31-T75

11¢1pp$0K

Will any LLM score at least 70% on Humanity's Last Exam before Dec 31, 2026?: At least 70%

KXLASTEXAM-26DEC31-T70

20¢2pp$0K

Will any LLM score at least 55% on Humanity's Last Exam before Dec 31, 2026?: At least 55%

KXLASTEXAM-26DEC31-T55

88¢+1pp$0K

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

KXLASTEXAM-26DEC31-T50

97¢+5pp$0K

Analysis

This contract reflects the likelihood that at least one large language model will achieve 60% or higher on Humanity's Last Exam by the end of 2027. The 89% probability suggests significant market confidence in near-term progress, though the contract ladder—where 70%, 75%, and 80% thresholds trade substantially lower—indicates uncertainty about how far performance will advance. The main drivers are current LLM capability trajectories and the specific difficulty of Humanity's Last Exam, which tests reasoning across humanities, sciences, and mathematics. Key upward pressure comes from demonstrated quarterly improvements in state-of-the-art models; downward pressure would stem from plateauing performance or test design that proves resistant to current training approaches. Resolution depends on actual benchmark results when major labs publish scores against this exam before year-end 2027.

  • Current leading LLM models are already scoring in the 50-60% range on similar benchmarks, making a 60% threshold plausible within 18 months
  • The step-down from 60% (89¢) to 70% (69¢) suggests markets expect meaningful but not exponential gains over the period
  • The exam's specific domain coverage and design methodology will significantly affect achievability—different test designs may have different inherent ceiling effects for current architectures
  • Major model releases and benchmark publications scheduled before December 2027 will be primary resolution drivers
  • The contract implies roughly 11% probability that no model reaches 60% despite rapid historical improvement rates, suggesting non-trivial concerns about performance saturation or fundamental architectural limits

What moved the line

  • Aug 19At least 50%17pp9881¢ · Kalshi
  • Aug 19At least 55%12pp8977¢ · Kalshi
  • Aug 20At least 55%10pp7787¢ · Kalshi
  • Aug 17At least 80%8pp3139¢ · Kalshi
  • Aug 19At least 70%7pp2417¢ · Kalshi

Recently closed in general

These markets stopped trading. Last odds and any captured outcome are shown above — full settlement detail lives at the venue.

More like this

Adjacent prediction questions.

How we compute these odds

SimpleFunctions aggregates live prediction-market contracts from Kalshi and Polymarket. Each slug groups contracts that resolve on the same underlying event, identified by venue event_id.

For binary slugs, the headline probability is the liquidity-weighted mid-price across all bound contracts. For multi-outcome slugs (e.g. elections with 3+ candidates), the headline is the leader’s price; we never arithmetically average disjoint outcomes — that would produce a number with no real-world meaning.

Snapshots refresh every 5 minutes during market hours; daily aggregates are computed at 04:00 UTC. The 30-day sparkline is drawn from per-ticker daily means stored in market_indicator_daily; 24h delta and movement events are derived from the same source.

Last updated on this page: just now.