Will an LLM score >=95% on SimpleBench before 2028? | Manifold

Will an LLM score >=95% on SimpleBench before 2028?

12

Ṁ100Ṁ315

2027

72%

chance

1H

6H

1D

1W

1M

ALL

This market will be resolved as YES if the AVG@5 score of any LLM on this leaderboard will be 95.0% or higher before Jan 1, 2028.

Market context

Get

1,000

to start trading!

People are also trading

Will LLMs become a ubiquitous part of everyday life by June 2026?

+3% 1d92% chance

Will the highest-scoring LLM on Dec 31, 2026 show <10% improvement over 2025's best average benchmark performance?

Will an LLM score >=85% on FrontierMath Tier 4 before 2028?

Will an LLM improve its own ability along some important metric well beyond the best trained LLMs before 2026?

Will an LLM be able to solve the Self-Referential Aptitude Test before 2027?

Will there by a major breakthrough in LLM continual learning before 2027?

Which LLM Maker will hold the top Safety Score for Spiral-Bench on https://eqbench.com/spiral-bench.html on Jan1, 2027?

Will there be any major breakthrough in LLM continual learning before 2028?

Will there be any major breakthrough in LLM continual learning before 2029?

Will there be a state-of-the-art LLM that is NOT based on next raw token prediction before 2029?

Related questions

Will LLMs become a ubiquitous part of everyday life by June 2026?

Will the highest-scoring LLM on Dec 31, 2026 show <10% improvement over 2025's best average benchmark performance?

Will an LLM score >=85% on FrontierMath Tier 4 before 2028?

Will an LLM improve its own ability along some important metric well beyond the best trained LLMs before 2026?

Will an LLM be able to solve the Self-Referential Aptitude Test before 2027?

Will there by a major breakthrough in LLM continual learning before 2027?

Which LLM Maker will hold the top Safety Score for Spiral-Bench on https://eqbench.com/spiral-bench.html on Jan1, 2027?

Will there be any major breakthrough in LLM continual learning before 2028?

Will there be any major breakthrough in LLM continual learning before 2029?

Will there be a state-of-the-art LLM that is NOT based on next raw token prediction before 2029?