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

> At least 50% leads at 97%, runner-up 89% across 16 winner-take-all outcomes — refreshed 58 min ago.

URL: https://simplefunctions.dev/odds/lastexam
Updated: 2026-08-24T04:20:51.758Z
Category: general
Status: active
Closes: 2027-12-31

## Headline

- Leader: At least 50% at 97%
- Runner-up: At least 55% at 89%
- Outcomes: 16 (winner-take-all)
- Venue: Kalshi (16 contracts)
- 24h volume: $0

## Bound contracts (16)

| Outcome | Price | 24h | Volume | Venue | Slug |
|---|---|---|---|---|---|
| At least 50% | 97¢ | +5pp | $0 | kalshi | /markets/will-any-llm-score-at-least-50-on-humanitys-last-e-kalshi-kxlastexam-26dec31-t50 |
| At least 55% | 89¢ | ±0 | $0 | kalshi | /markets/will-any-llm-score-at-least-55-on-humanitys-last-e-kalshi-kxlastexam-26dec31-t55 |
| At least 60% | 87¢ | ±0 | $0 | kalshi | /markets/will-any-llm-score-at-least-60-on-humanitys-last-e-kalshi-kxlastexam-27dec31-t60 |
| At least 65% | 79¢ | ±0 | $0 | kalshi | /markets/will-any-llm-score-at-least-65-on-humanitys-last-e-kalshi-kxlastexam-27dec31-t65 |
| At least 70% | 62¢ | ±0 | $0 | kalshi | /markets/will-any-llm-score-at-least-70-on-humanitys-last-e-kalshi-kxlastexam-27dec31-t70 |
| At least 60% | 62¢ | +1pp | $0 | kalshi | /markets/will-any-llm-score-at-least-60-on-humanitys-last-e-kalshi-kxlastexam-26dec31-t60 |
| At least 75% | 57¢ | ±0 | $0 | kalshi | /markets/will-any-llm-score-at-least-75-on-humanitys-last-e-kalshi-kxlastexam-27dec31-t75 |
| At least 80% | 39¢ | ±0 | $0 | kalshi | /markets/will-any-llm-score-at-least-80-on-humanitys-last-e-kalshi-kxlastexam-27dec31-t80 |
| At least 65% | 31¢ | +1pp | $0 | kalshi | /markets/will-any-llm-score-at-least-65-on-humanitys-last-e-kalshi-kxlastexam-26dec31-t65 |
| At least 85% | 25¢ | ±0 | $0 | kalshi | /markets/will-any-llm-score-at-least-85-on-humanitys-last-e-kalshi-kxlastexam-27dec31-t85 |
| At least 70% | 21¢ | +1pp | $0 | kalshi | /markets/will-any-llm-score-at-least-70-on-humanitys-last-e-kalshi-kxlastexam-26dec31-t70 |
| At least 90% | 19¢ | +1pp | $0 | kalshi | /markets/will-any-llm-score-at-least-90-on-humanitys-last-e-kalshi-kxlastexam-27dec31-t90 |
| At least 95% | 11¢ | +1pp | $0 | kalshi | /markets/will-any-llm-score-at-least-95-on-humanitys-last-e-kalshi-kxlastexam-27dec31-t95 |
| At least 75% | 11¢ | −1pp | $0 | kalshi | /markets/will-any-llm-score-at-least-75-on-humanitys-last-e-kalshi-kxlastexam-26dec31-t75 |
| At least 80% | 6¢ | ±0 | $0 | kalshi | /markets/will-any-llm-score-at-least-80-on-humanitys-last-e-kalshi-kxlastexam-26dec31-t80 |
| At least 85% | 3¢ | ±0 | $0 | kalshi | /markets/will-any-llm-score-at-least-85-on-humanitys-last-e-kalshi-kxlastexam-26dec31-t85 |

## 30-day trajectory

| Day | At least 50% | At least 55% | At least 60% |
|---|---|---|---|
| 2026-07-25 | 98 | 76 | — |
| 2026-07-26 | 97 | 84 | 87 |
| 2026-08-07 | 98 | 92 | 89 |
| 2026-08-10 | — | 92 | 88 |
| 2026-08-17 | — | 88 | 87 |
| 2026-08-19 | 81 | 77 | 87 |
| 2026-08-20 | 86 | 87 | 87 |
| 2026-08-23 | — | 89 | 87 |

_29 days of price history captured. Each row is the daily mean of intraday 5-min captures._

## What moved the line

- 2026-08-19 · At least 50% −17pp 98→81¢ · kalshi
- 2026-08-19 · At least 55% −12pp 89→77¢ · kalshi
- 2026-08-20 · At least 55% +10pp 77→87¢ · kalshi
- 2026-08-17 · At least 80% +8pp 31→39¢ · kalshi
- 2026-08-17 · At least 65% +7pp 72→79¢ · kalshi

## 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.

### Key factors

- 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

## Methodology

Headline is the **leader's price**, not an arithmetic mean — averaging disjoint winner-take-all outcomes is meaningless. Per-outcome prices come from the venue's last-traded mid; cross-venue values are simple means across contracts on each venue.

## How to use this data

- HTML: https://simplefunctions.dev/odds/lastexam
- JSON: https://simplefunctions.dev/api/public/odds?slug=lastexam

## License

CC-BY-4.0. Attribute "SimpleFunctions" with a link to https://simplefunctions.dev. See https://simplefunctions.dev/legal for terms.