---
title: "PACE proxy cuts agentic eval cost to 1% of full suite"
slug: "pace-proxy-cuts-agentic-eval-cost-to-1-of-full-suite"
published: "2026-07-31"
beat: "Research"
tags: ["Research"]
creator: "Agentry Newsroom"
editor: "Susanne Sperling, Editor — Human in the Loop"
tools: ["Claude (Anthropic)", "Perplexity Sonar"]
creativeWorkStatus: "verified"
dateReviewed: "2026-07-31"
aiActArticle50: "compliant"
humanView: "https://agentry.news/research/pace-proxy-cuts-agentic-eval-cost-to-1-of-full-suite"
agentView: "https://agentry.news/agent/pace-proxy-cuts-agentic-eval-cost-to-1-of-full-suite"
---# PACE proxy cuts agentic eval cost to 1% of full suite

> Researchers at NeuLab published PACE, a proxy benchmark method that predicts agentic model performance with under 4% error and 85% ranking accuracy across 14 models, reducing evaluation cost to 1% of 

*Drafted by an AI agent. Verified by Susanne Sperling, Editor — Human in the Loop. [AI policy](/ai-policy).*

## Researchers publish PACE proxy to slash agentic evaluation cost

A new arXiv paper proposes PACE, a method for predicting how well language models perform on agentic tasks without running expensive full evaluations [arXiv](https://arxiv.org/abs/2607.02032). The technique constructs lightweight proxy benchmarks by selecting instances from existing non-agentic evaluations and fitting regression models to map those scores onto agentic benchmark performance.

The approach addresses a real friction point in the agent economy: running comprehensive agentic benchmarks—which require agents to execute multi-step tasks in real or simulated environments—is computationally expensive and time-consuming. PACE promises to unlock faster model comparison and ranking cycles for teams shipping agent products and infrastructure.

## Benchmark results across 14 models

The PACE paper reports validation across **14 models**, **4 agentic benchmarks**, and **19 non-agentic benchmarks** [arXiv](https://arxiv.org/abs/2607.02032). The core findings: **leave-one-out cross-validation MAE under 4%**, **Spearman rank correlation above 0.80**, and **pairwise model-ranking accuracy around 85%**. These metrics suggest the proxy accurately estimates which models will rank highest on true agentic tasks.

The method's cost profile is the headline draw: PACE evaluation runs at **less than 1% of the cost** of full agentic evaluation [arXiv](https://arxiv.org/abs/2607.02032). For teams iterating on model selection, safety testing, or capability benchmarking, that efficiency unlock could compress evaluation cycles from weeks to hours.

## Why this matters for the agent economy

Agent builders today face a choice: spend heavily on comprehensive benchmarking to trust a model's real-world capability, or make quick calls on limited signals. PACE sits between those poles—fast enough to use in pre-selection workflows, accurate enough to avoid ranking surprises downstream. The paper does not claim proxy results should replace full agentic evaluation for production safety gates; rather, it positions PACE as a filter to shrink the candidate pool before expensive final testing.

The work also opens a research direction: as more agentic benchmarks stabilize and scale, proxy construction should improve. Right now PACE is bounded by the diversity and quality of non-agentic benchmarks available; future versions could absorb richer signal from task families closer to real agent work.

Code and datasets are available via HuggingFace [HuggingFace](https://huggingface.co/datasets/neulab/pace-bench), enabling developers to replicate the method or apply it to proprietary model lineups.