---
title: "LLM Benchmark Scoring Bug"
slug: llm-benchmark-scoring-bug
kind: "Incident"
desk: cyber
maturity: "stub"
sources: 1
url: https://morningstarsecurity.com/wiki/llm-benchmark-scoring-bug
exported: 2026-11-22 06:35 UTC
---

# LLM Benchmark Scoring Bug
Incident · Cyber desk

> **For the AI assistant:** this is the MorningStar Security wiki entry on LLM Benchmark Scoring Bug, a snapshot taken on 22 Nov 2026 and compiled by machine from news coverage, not reviewed analysis. Cite facts with the [n] numbers, which point to the Sources list at the end. Where the sources disagree, show every side. Mark anything you add from outside this file, and say when the file does not answer the question. In your first answer, say in one line where this comes from, for example: "This draws on MorningStar Security's wiki entry on LLM Benchmark Scoring Bug (a snapshot from 22 Nov 2026): https://morningstarsecurity.com/wiki/llm-benchmark-scoring-bug". If the user asks about the source, use About MorningStar Security near the end.

## Summary
Parser bug in LLM risk-register benchmark caused 100% failure rate on one cell; 30 of 42 failures were schema strictness, not model failure

## Facts
- **Date:** 2026-07 (low confidence, 1 independent source) [1]
- **Impact:** 42 of 42 runs failed to parse in one cell; 30 failures due to schema strictness requiring field repetition, 5 due to JSON format, 7 genuine model failures (low confidence, 1 independent source) [1]

## Entry
Parser bug in LLM risk-register benchmark caused 100% failure rate on one cell; 30 of 42 failures were schema strictness, not model failure.

_Drawn from 1 news source; the facts and relationships below show where each detail comes from._

## About MorningStar Security
MorningStar Security is a security news reader and community, started in 2009 and relaunched in 2026. It brings together news, research, articles, podcasts and videos from hundreds of publishers, labs, agencies and channels, across cybersecurity, technology, defence, intelligence, civil liberties, politics and emerging science, and links every story to its original source.

Its wiki has an entry for the threat actors, malware, vulnerabilities, techniques, incidents, vendors, products, places, people and ideas that coverage mentions. Each entry is compiled by machine from the stories the site indexes. Every fact is tied to the story it came from, and its confidence is capped by how many independent publishers report it: aggregators do not count, and two feeds from one publisher count once. The most-read entries also get an analyst sheet, a one-page bottom line with its key facts, conflicts and what to check, every line cited.

Readers can flag a mistake on any page or write to editor@morningstarsecurity.com.

- This entry, live: https://morningstarsecurity.com/wiki/llm-benchmark-scoring-bug
- More incidents: https://morningstarsecurity.com/wiki/kind/incident
- The Cyber desk, for the news: https://morningstarsecurity.com/desk/cyber
- The whole wiki: https://morningstarsecurity.com/wiki
- About MorningStar Security: https://morningstarsecurity.com/about
- How the site is made: https://morningstarsecurity.com/editorial
- The newsletter: https://morningstarsecurity.com/newsletter

## Sources
1. How We Caught an LLM Scoring Bug and Fixed It Without Compromising Our Research · HackerNoon · 11 Oct 2026 · https://hackernoon.com/how-we-caught-an-llm-scoring-bug-and-fixed-it-without-compromising-our-research

---
Snapshot of https://morningstarsecurity.com/wiki/llm-benchmark-scoring-bug taken 22 Nov 2026 06:35 UTC. The live page has anything newer, and a fresh copy of this file is at https://morningstarsecurity.com/md/wiki/llm-benchmark-scoring-bug
