MTEB Leaderboard Adds Openness Metric; LightOn Scores 100%
antoine_chaffin · x · 2026-08-03
The MTEB leaderboard has introduced a new "openness" metric to evaluate how open models are regarding license, training data, paper, and code. LightOn's models achieved a perfect 100% score. The author notes that while releasing powerful models is cool, giving the community the tools to reproduce, audit, and enhance them is even better.
Related event: MTEB Adds Openness Metric; LightOn Model Scores Perfectly(2 posts)→
More from Models
- DeepSeek Models Tested: 242 One-shot Outputs Compared — kms_dev · 2026-08-03
- MiniMax H3 Tested: Users Report Censored Video Generation — DaLyon92x · 2026-08-03
- Google AI Mode Becomes Rigid Due to Over-Optimization for Safety and Shopping — Build-your-own-2020 · 2026-08-03
- AI Educator Teams Up with Hugging Face for Open Model Series — HarperSCarroll · 2026-08-03
- Anthropic Investigating Degraded Performance Issue on Claude Sonnet 5 — ClaudeAI-mod-bot · 2026-08-03
- User extracts internal system prompt of Google Gemini — Empty_Paramedic_5957 · 2026-08-03