Will any open-source model achieve GPT-4 level performance on MMLU through 2024?

Question

GPT-4 currently leads the Multi-task language understanding benchmark [1] at 86.4% [2]. Will any open-source language model achieve at least 86.4% on MMLU average?

A leaderboard of open-source models can be found here.

Manifold Markets · Accepted Answer

Yes — resolved on Dec 9, 2024 by Manifold Markets prediction market.