Harrier Sparks Controversy on MMTEB Leaderboard
antoine_chaffin · x · 2026-07-15
The post states that Harrier models achieved MMTEB top-1 in their parameter scale group and scored 62.18 / 66.35 / 69.32 on MIRACL.
However, the author argues that the current MMTEB leaderboard display does not align with user expectations for finding a good multilingual model:
- Some models are not strong overall but rank high due to using training sets from certain task datasets.
- This suggests that leaderboard results may reflect dataset memorization rather than generalization.
Subsequent replies further point out that two official MMTEB tasks themselves suffer from this issue.
Related event: MMTEB Leaderboard Faces Training Data Contamination Controversy(3 posts)→
More from Models
- GPT 6.1 Terra vs Claude Sonnet 5.5: speed and value vs raw capability — teortaxesTex · 2026-10-27
- Harmonic Teases: AI Taught to Prove Math, 'Something Harder' Coming Soon — satnam6502 · 2026-10-27
- OpenAI quietly swaps Plus/Pro default to cheaper GPT-6.1 Terra and cuts Codex allowance — kimmonismus · 2026-10-27
- 'Never been this uninterested after an OpenAI model release' — theteknosaur · 2026-10-27
- Dev questions reports of Chinese models writing insecure code, citing thin methods and conflicts — dbreunig · 2026-10-27
- Aidan Gomez: LLM probing outside servers was out-of-bounds, not proof of intent — AccBalanced · 2026-10-27