---
type: "raw_signal"
id: "artificial-analysis-publishes-per-benchmark-results-with-the-7dc67e"
slug: "artificial-analysis-publishes-per-benchmark-results-with-the-7dc67e"
title: "Artificial Analysis publishes per-benchmark results with the index and documents task construction, scoring, and model handling in its methodology ."
description: "Artificial Analysis has published a methodology page for its Decision Index that specifies the four component evaluations, their equal 25% weights, and how tasks and answers are handled."
retrieval_nugget: "Artificial Analysis has published a methodology page for its Decision Index that specifies the four component evaluations, their equal 25% weights, and how tasks and answers are handled."
observed_at: "2026-10-14"
record_date: "2026-10-14"
date_kind: "observed_at"
why_it_matters: "Source: https://artificialanalysis.ai/methodology/decision-index"
novelty: "notable"
verification_level: "source-linked"
signal_type: "research"
source_platform: "artificialanalysis.ai"
topics: []
entities: ["Artificial Analysis","Artificial Analysis Decision Index","AA-Omniscience-Decision","HLE-MultiChoice","When2Call","WildGuardTest","Humanity's Last Exam"]
related_patterns: []
source_url: "https://artificialanalysis.ai/methodology/decision-index"
source_urls: ["https://artificialanalysis.ai/methodology/decision-index"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:artificial-analysis-publishes-per-benchmark-results-with-the-7dc67e"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/artificial-analysis-publishes-per-benchmark-results-with-the-7dc67e/","markdown":"https://newruntime.com/signals/artificial-analysis-publishes-per-benchmark-results-with-the-7dc67e.md","json":"https://newruntime.com/signals/artificial-analysis-publishes-per-benchmark-results-with-the-7dc67e.json"}
---

# Artificial Analysis publishes per-benchmark results with the index and documents task construction, scoring, and model handling in its methodology .

## Retrieval answer

Artificial Analysis has published a methodology page for its Decision Index that specifies the four component evaluations, their equal 25% weights, and how tasks and answers are handled.

Artificial Analysis has published a methodology page for its Decision Index that specifies the four component evaluations, their equal 25% weights, and how tasks and answers are handled. The components are AA-Omniscience-Decision, HLE-MultiChoice, When2Call, and WildGuardTest, covering knowledge and hallucination, reasoning, tool calling, and classification.

The page says AA-Omniscience-Decision uses 500 private questions with four candidate answers plus “I don't know”; accuracy and non-hallucination rate each contribute 12.5 percentage points to the index. HLE-MultiChoice uses 513 text-only multiple-choice questions from Humanity's Last Exam. It also distinguishes the response handling for decision models from language models, including structured outputs for the latter.

The disclosure makes the aggregate index easier to inspect and interpret, but does not establish that its task mix represents every deployment context. Teams can use it as a shortlist and should validate leading candidates against their own labels, traffic, and error costs.

Source: https://artificialanalysis.ai/methodology/decision-index

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)