---
schema_version: "newruntime-agent-readable-v0.2"
type: "capability_delta"
stable_id: "capability_delta:a-public-index-makes-decision-models-comparable"
slug: "a-public-index-makes-decision-models-comparable"
title: "A public index makes decision models comparable"
description: "Artificial Analysis launched a Decision Index for models that choose among fixed options, and published its methodology. Builders can now compare performance across classification, tool calling, knowledge, and reasoning tasks."
retrieval_nugget: "Artificial Analysis launched a Decision Index for models that choose among fixed options, and published its methodology. Builders can now compare performance across classification, tool calling, knowledge, and reasoning tasks."
status: "published"
observed_at: "2026-10-17"
record_date: "2026-10-17"
date_kind: "observed_at"
before_capability: "Builders had no cited public composite index for comparing models that select among fixed options."
enabling_change: "Artificial Analysis launched Decision Index v1.0 and published its methodology, including component evaluations, weights, task construction, and scoring."
after_capability: "Builders can consult a documented composite benchmark to compare decision models across four evaluation areas."
human_consequence: "Model selection can draw on a shared benchmark and its scoring details rather than relying only on informal comparisons."
verification_level: "source-inspected"
buildability_class: "B1"
bottleneck: "The items establish a published index and methodology, not that its tasks predict performance in a builder’s own use cases."
related_shift: "compute-backed-ai-contracts"
related_posts: []
topics: []
source_urls: ["https://newruntime.com/signals/artificial-analysis-publishes-per-benchmark-results-with-the-7dc67e/","https://newruntime.com/signals/artificial-analysis-launched-the-decision-index-v1-0-92b332/"]
featured: false
supporting_evidence: [{"title":"Artificial Analysis publishes per-benchmark results with the index and documents task construction, scoring, and model handling in its methodology .","url":"https://newruntime.com/signals/artificial-analysis-publishes-per-benchmark-results-with-the-7dc67e/","kind":"signal","observed_at":"2026-10-17"},{"title":"Artificial Analysis launched the Decision Index v1.0 , benchmarking decision models on classification, tool calling, knowledge, and reasoning.","url":"https://newruntime.com/signals/artificial-analysis-launched-the-decision-index-v1-0-92b332/","kind":"signal","observed_at":"2026-10-17"}]
routes: {"html":"https://newruntime.com/deltas/a-public-index-makes-decision-models-comparable/","markdown":"https://newruntime.com/deltas/a-public-index-makes-decision-models-comparable.md","json":"https://newruntime.com/deltas/a-public-index-makes-decision-models-comparable.json"}
source_format: "knowledge-ledger"
published_at: "2026-10-19T06:00:43.068Z"
auto_created: true
editorial_provenance: {"desk":"knowledge-revision","provider":"codex","model":"gpt-6-luna","created_at":"2026-10-19T06:00:43.068Z","week_start":"2026-10-12","review":"auto-created from reviewed evidence; the owner may revise or retire it"}
---

# A public index makes decision models comparable

## Retrieval answer

Artificial Analysis launched a Decision Index for models that choose among fixed options, and published its methodology. Builders can now compare performance across classification, tool calling, knowledge, and reasoning tasks.

## Capability change

- Before: Builders had no cited public composite index for comparing models that select among fixed options.
- Enabling change: Artificial Analysis launched Decision Index v1.0 and published its methodology, including component evaluations, weights, task construction, and scoring.
- After: Builders can consult a documented composite benchmark to compare decision models across four evaluation areas.

Human consequence: Model selection can draw on a shared benchmark and its scoring details rather than relying only on informal comparisons.

Bottleneck: The items establish a published index and methodology, not that its tasks predict performance in a builder’s own use cases.

Buildability: B1. Verification: source-inspected. Related shift: [compute-backed-ai-contracts](https://newruntime.com/shifts/compute-backed-ai-contracts/).

The index launch and methodology publication are complementary evidence for one change: a composite evaluation of decision models, with its task and scoring approach documented. This makes the comparison more inspectable than a leaderboard alone.

A builder can use the published index as one input when evaluating models that choose among fixed options. The items do not establish that its benchmark generalizes to production tasks, so watch for evidence of task coverage and real-world predictive value.

Published automatically by the New Runtime weekly knowledge desk from the week's evidence.

## Supporting evidence

- [Artificial Analysis publishes per-benchmark results with the index and documents task construction, scoring, and model handling in its methodology .](https://newruntime.com/signals/artificial-analysis-publishes-per-benchmark-results-with-the-7dc67e/) (signal, 2026-10-17)
- [Artificial Analysis launched the Decision Index v1.0 , benchmarking decision models on classification, tool calling, knowledge, and reasoning.](https://newruntime.com/signals/artificial-analysis-launched-the-decision-index-v1-0-92b332/) (signal, 2026-10-17)

## Provenance

Auto-created by the New Runtime weekly knowledge desk on 2026-10-19 from evidence reviewed in the week of 2026-10-12. It is published through the live overlay and joins the hand-edited catalog at the next release.