cs.LGNov 18, 2026

The 7th International Verification of Neural Networks Competition (VNN-COMP 2026): Summary and Results

Authors: Tobias Ladner, Konstantin Kaulen, Stanley Bak, Julien Girard-Satabin, Taylor T. Johnson, Edoardo Manino, ThanhVu H Nguyen, Ben Wooding, 

Organizations: Technical University of Munich, Munich, Germany · RWTH Aachen University, Aachen, Germany · Stony Brook University, Stony Brook, New York, USA · Universit´e Paris-Saclay, CEA, List, F-91120, Palaiseau, France · 

Abstract

This report summarizes the seventh International Verification of Neural Networks Com- petition (VNN-COMP 2026), held as part of the Symposium on AI Verification (SAIV) co-located with the International Conference on Computer-Aided Verification (CAV) at FLoC 2026 in Lisbon, Portugal. The goal of the competition is to provide an objective comparison of the state-of-the-art methods in neural network verification, in terms of scal- ability and speed. Along this line, we used standard formats (ONNX for neural networks and VNNLIB for specifications), standard hardware (all tools are run by the organizers on AWS), and tool parameters provided by the tool authors. This report summarizes the rules, benchmarks, participating tools, results, and lessons learned from this competition.

Figures & tables

Explore similar work

CardsList
  1. VNN-LIB 2.0: Rigorous Foundations for Neural Network Verification

    May 8, 2026Ann Roy, Allen Antony, Andrea Gimelli +1Neural Network VerificationFormal Verification

  2. NNV3: Expanding Neural Network Verification to New Architectures and Domains

    Sep 24, 2026Anne M. Tumlin, Samuel Sasaki, Ben Wooding +8Neural Network VerificationReachability Analysis

  3. Exploring Solver-Level Warmstarting for Neural Network Verification

    Sep 22, 2026Annelot Bosman, Minghao Liu, Marta Kwiatkowska +2Neural Network Verification