VeriLoop E2 is now available, bringing verifier-governed reasoning to code, mathematics, and physics in a 27B open-weight model.
๐ค
๐ The evaluated E2 system scores 76.2% on SWE-bench Pro, 88.8% on Terminal-Bench 2.1, 98.3% on AIME 2026, 93.9% on GPQA Diamond, and 89.6% on Apex 2025.
๐ VeriLoop-Governed Recurrence proposes candidates, verifies them externally, and commits only improvements without regression.
๐งช Two evidence-backed scientific demonstrations cover a 67.35% Riemann ฮถ zero-proportion certificate and Asymptotic Graviton Tomography. Neither claims to solve the underlying open problem.
๐ Built on Qwen3.8-27B with a 262K native context window and OpenAI-compatible vLLM serving validated at 131K.
๐ Model weights and public inference utilities: Apache 2.0. The production VeriLoop Harness is not included, and the scientific artifacts carry separate terms.