Hugging Face's official benchmark leaderboards are updated daily, tracking over 1,100 entries across 50+ benchmarks as of October 24, 2026. Recent updates include the addition of new benchmarks like decision-index-leaderboard and decision-index-vision-leaderboard. The data reflects self-reported scores from model authors, with some entries marked as verified by Hugging Face. QuantID, a technology partner of VIDRAFT, publishes these updates, noting that the rankings are based on public API data and not independent evaluations. AI
IMPACT Provides ongoing visibility into model performance on various benchmarks, aiding developers in tracking progress and identifying top-performing models.
RANK_REASON Daily updates to leaderboards are a recurring event, not a novel release or significant industry shift.
- decision-index-leaderboard
- decision-index-vision-leaderboard
- deepseek-ai/DeepSeek-V4.1-Flash
- deepseek-ai/DeepSeek-V4.1-Flash-1017
- FINAL-Bench
- Hugging Face
- VIDRAFT
- XiaomiMiMo/MiMo-V2.6-Pro-RL
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →