# Artificial Analysis finds tools lift VIALS-AA scores, letting Claude Haiku 5.5 beat Fable 5.2

> Original title: Take away its tools, and Claude Fable 5.2 scores below Claude Haiku 5.5 with tools on VIALS-AA; across models tool use nearly doubles sco...

- Source: Artificial Analysis
- Published: 2026-11-11T23:46:45.000Z
- Bad Influence: https://badinfluence.news/items/qjxfcrn4xr7mymqfoxow6w2tw
- Original: https://x.com/ArtificialAnlys/status/2120664556972257506

## Summary

Artificial Analysis reran its VIALS-AA visual reasoning benchmark without tools and found tool use nearly doubles average scores, from about 25% to 47%. Without tools, Claude Fable 5.2 (max) drops from 67% to 44%, falling below Claude Haiku 5.5 (max) at 49% with tools. Haiku costs $0.07 per task, about a tenth of Fable's $0.73 cost without tools.

## Post

Take away its tools, and Claude Fable 5.2 scores below Claude Haiku 5.5 with tools on VIALS-AA; across models tool use nearly doubles scores, from ~25% to ~47% on average

VIALS-AA is our implementation of @joinHandshakeAI's VIALS benchmark for visual reasoning in life sciences research. By default, models work as agents: they think, run code and view images in a sandbox. We reran VIALS-AA in a one-shot format: one request with the question and images, and no tools.

Lower cost models in an agent harness can beat single-shot large models on both cost and performance in visual reasoning and interpretation of scientific artifacts.

Claude Fable 5.2 (max) leads VIALS-AA at 67% with tools, at a cost of $4.20 per task; without tools it scores 44% at $0.73 per task. Claude Haiku 5.5 (max) scores 49% with tools, at $0.07 per task: higher than Fable without tools, at about a tenth of the cost.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHW4bQNBWUAAEgGF.jpg&mode=thumb&exp=1794787200&sig=86b367fa49257c9a)