MMTEB Leaderboard Suffers from Training Set Contamination

antoine_chaffin · x · 2026-07-15

This post highlights that ranking by SpartQA and MIRACL yields interesting yet "dangerous" results.

Replies clarify that these are official tasks on the MMTEB leaderboard. Currently, no model achieves naturally high scores on these tasks unless it was trained directly on these specific datasets. Essentially, some high scores reflect data leakage/memorization rather than true generalization; some "global #1" models might actually perform worse overall on other tasks.

Related event: MMTEB Leaderboard Faces Training Data Contamination Controversy(3 posts)→

Original post →

More from Research

Research channel →