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
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11