Agent Reading Test

A benchmark that tests how well AI coding agents can read web content. Point your agent at the test, get a score, compare across platforms.

AI coding agents (Claude Code, Cursor, GitHub Copilot, and others) read documentation websites as part of their workflows. But most agents hit silent failure modes: content gets truncated, CSS buries the real text, client-side rendering delivers empty shells, and tabbed content serializes into walls of text where only the first variant is visible.

This benchmark surfaces those failure modes. Each test page is designed around a specific problem documented in the Agent-Friendly Documentation Spec. The pages embed canary tokens at strategic positions. But instead of asking agents to hunt for tokens (which games relevance filters), the test gives the agent realistic documentation tasks. Only after the agent completes all tasks does it learn about the canary tokens and report which ones it encountered. You paste the results into a scoring form.

agentreadingtest.com/start/

and tell it to follow the instructions. Go to https://agentreadingtest.com/start/ and follow the instructions

1. Truncation: 150K-char page with canary tokens at 10K, 40K, 75K, 100K, and 130K. Maps exactly where your agent's truncation limit kicks in.
2. Inline CSS: 80K of inline CSS before the real content. Tests whether agents distinguish CSS noise from documentation.
3. Client-side Rendering: Client-side rendered page. Content only appears after JavaScript executes. Most agents see an empty shell.
4. Tabbed Content: 8 language variants in tabs. Canary tokens in tabs 1, 4, and 8. Tests how far into serialized tab content the agent reads.
5. Soft 404: Returns HTTP 200 with a "page not found" message. Tests whether the agent recognizes it as an error page.
6. Broken Markdown: Markdown with an unclosed code fence. Everything after it becomes "code." Tests markdown parsing awareness.
7. Format Negotiation: Different canary tokens in HTML vs. markdown versions. Tests whether your agent requests the better format.
8. Redirects: 301 redirect to a different hostname. Most agents won't follow it (security measure). The canary is on the other side.

The test has a maximum score of 20 points. Each canary token found earns 1 point, and correct answers to qualitative questions earn 1 point each. The answer key has the full breakdown.

A perfect score is unlikely for any current agent. The tests are calibrated so that each failure mode will realistically affect at least some agents. A typical score range for current agents is probably 14-18 out of 20, depending on the platform's web fetch pipeline.

Agent Reading Test is a companion project to the Agent-Friendly Documentation Spec, which defines 22 checks across 8 categories evaluating how well documentation sites serve AI agent consumers. The spec is grounded in empirical observation of real agent workflows.

This benchmark flips the perspective: instead of testing the documentation site, it tests the agent. The same failure modes apply, but here we're measuring which agents handle them gracefully and which don't.

Source code: github.com/agent-ecosystem/agent-reading-test