ZTC Models: JEV ecosystems
Collection
Answer verification from one forward pass, zero generated tokens. Measured against JEV and 10 others on 2,018 identical items. • 7 items • Updated • 32
master PRO
fantos
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
FINAL-Bench/ZTC-Judge-4B liked a model 1 day ago
FINAL-Bench/ZTC-Judge-9B reacted to SeaWolf-AI's post with 🚀 1 day ago
Ask a language model how confident it is and you get an AUC of 0.5000. Exactly a coin flip. We measured it across 2,018 items.
https://huggingface.co/spaces/FINAL-Bench/gate-tetris
https://huggingface.co/blog/FINAL-Bench/ztc
Collection: https://huggingface.co/collections/FINAL-Bench/ztc-models-jev-ecosystems
Zero-Token Confidence (ZTC) reads it. One forward pass over the model's hidden state returns a calibrated probability that the answer is correct. Zero generated tokens.
It sits at the top of the shared board. Same 2,018 items, same harness for every entry: ZTC on Darwin-397B 0.7394, JEV 0.7335, ZTC-Judge-27B 0.7255, a surface baseline that reads only answer length and formatting 0.7036, Lynx 8B 0.5157, the model's own self-reported confidence 0.5000, HHEM 0.4852. First and third place both emit nothing at all.
The number worth staring at is 0.7036. That is a baseline reading no content whatsoever, just how long the answer is and how it is formatted. Any verifier scoring below it is not reading content either.
On speed, one gate call costs 0.0615 seconds, measured on four B200s across 2,000 items. Generating a single candidate answer takes 1.631 seconds, so the gate is 26 times cheaper than the work it guards. A verifier that generates competes with your agent for the same budget. A verifier that only reads can be attached to every action instead of a sampled few.
We built it so you can watch it decide. Three lanes receive the same stream of proposed actions and the same time budget. One has no gate and must execute everything. One uses a text-reading verifier. One uses ZTC. Right action plus one, wrong action minus one, hold zero. Over 400 matches: no gate minus 3.9, text verifier plus 13.0, ZTC plus 29.1, with ZTC taking 98 percent of matches. Gating lifts executed accuracy from 49 percent to 65 percent.
Organizations
upvoted a collection 2 days ago
upvoted a collection 8 days ago
upvoted a collection 27 days ago
upvoted 2
papers 28 days ago
The Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models
Paper • 2608.22876 • Published • 14
A Numerical Realization of Suzuki's Weil-Quadratic-Form Operator: The Archimedean Spectral Law, its Universality, and an Operator Form of Weil's Positivity Criterion
Paper • 2607.24830 • Published • 8
upvoted a collection about 1 month ago
upvoted a paper 2 months ago
upvoted a collection 2 months ago
upvoted 2
articles 3 months ago
Article
Chitos: From Detection to Proof — An Autonomous Security AI That Actually Exploits
FINAL-Bench
• • 19 Article
FINAL-Bench Quantum: An Open, Neutral Benchmark for Quantum-Computing Methods
FINAL-Bench
• • 17 upvoted a paper 4 months ago
upvoted 5
collections over 1 year ago