Sentient Foundation launches open Fingerprinting Leaderboard for model provenance
0xsachi · x · 2026-10-14
Sentient Foundation released the Fingerprinting Leaderboard, a free open-source benchmark for proving a model was copied from yours. Researchers submit ownership-marking methods; Sentient plants the mark in its own test models, tries to strip it, and ranks methods publicly, with the test code mlprints also released. A fingerprint trains a model to return unlikely answers to secret prompts, verifiable via API alone. The board scores verification reliability alongside removal resistance (robustness) and skill retention (utility). Current top method llmap-v4 scores 100/100/99%.
More from Models
- Rejected by NeurIPS: study shows a single test-set replica beats uncontaminated irreducible error — RylanSchaeffer · 2026-10-15
- New SWE-bench Multimodal leaderboard: Claude Opus 5.5 leads at 70.21% on visual bugs — OfirPress · 2026-10-15
- Google says Gemini 4 Argon is delivering breakthroughs in quantum computing, fusion and protein design — GoogleDeepMind · 2026-10-15
- Google sits down with Sergey Brin to discuss Gemini 4 Argon and the road ahead — OfficialLoganK · 2026-10-15
- ChatGPT quietly makes GPT-6.1 Sol the default, users report sharper voice chats — shaunralston · 2026-10-15
- The small-model world has changed forever, but the builder community hasn't priced it in — tokenbender · 2026-10-15