---
title: "Docs Benchmark Report: Deepgram"
description: "Deepgram benchmark report with category scores and check-level detail."
canonical: "https://docsalot.dev/benchmarks/docs/deepgram"
human_url: "https://docsalot.dev/benchmarks/docs/deepgram"
markdown_url: "https://docsalot.dev/benchmarks/docs/deepgram.md"
index_url: "https://docsalot.dev/benchmarks/docs"
index_markdown_url: "https://docsalot.dev/benchmarks/docs.md"
updated: "2026-05-04"
---

[Back to docs benchmark index](https://docsalot.dev/benchmarks/docs.md)

# Docs Benchmark Report: Deepgram

> Copy this markdown report into a developer ticket or coding agent prompt when you want concrete docs fixes tied to benchmark checks.

## Report Links

- Human report: https://docsalot.dev/benchmarks/docs/deepgram
- Markdown report: https://docsalot.dev/benchmarks/docs/deepgram.md
- Benchmark index: https://docsalot.dev/benchmarks/docs
- Benchmark index markdown: https://docsalot.dev/benchmarks/docs.md
- Public docs URL: https://developers.deepgram.com/docs

## Score Summary

- Report for: Deepgram
- Display URL: developers.deepgram.com/docs
- Report type: Public benchmark report
- Score: 95
- Grade: A
- Summary: Deepgram scored 95/100 on Fern's public Agent Score report across 22 published checks.
- Checked at: May 4, 2026 at 9:03 PM UTC
- Category: AI
- Source: Fern Agent Score
- Checks passed: 16/22
- Warnings: 3
- Failed checks: 2
- Skipped checks: 1

## What Already Works

- URL Stability and Redirects is relatively strong at 100/100.
- Authentication and Access is relatively strong at 100/100.
- Content Structure is relatively strong at 100/100.

## What To Improve Next

- Markdown Content Parity in Observability and Content Health.
- Page Size Html in Page Size and Truncation Risk.
- LLMS TXT Valid in Content Discoverability.

## Full Score Breakdown

### Page Size and Truncation Risk - 98/100

- Question: Can an agent read the page without losing important context?
- Category focus: Checks for oversized pages, noisy navigation, and chunking risks.
- Category note: 1 failed check still shape this area.
- Passed: 3
- Warnings: 0
- Failed: 1
- Skipped: 0

Checks:
- PASS - Rendering Strategy: All 10 sampled pages contain server-rendered content
- PASS - Page Size Markdown: All 9 pages under 50K chars (median 7K, max 15K)
- FAIL - Page Size Html: 1 of 10 sampled pages convert to over 100K chars (max 181K, 0% boilerplate)
- PASS - Content Start Position: Content starts within first 10% on all 10 sampled pages (median 0%)

### Observability and Content Health - 90/100

- Question: Can an agent tell whether the docs are fresh and trustworthy?
- Category focus: Checks for freshness signals, content health, and crawl confidence.
- Category note: 1 failed check still shape this area.
- Passed: 2
- Warnings: 0
- Failed: 1
- Skipped: 0

Checks:
- PASS - LLMS TXT Freshness: llms.txt covers 100% of 228 sitemap doc pages
- FAIL - Markdown Content Parity: 1 of 9 pages have substantive content differences between markdown and HTML (avg 10% missing)
- PASS - Cache Header Hygiene: All 12 endpoints have appropriate cache headers

### URL Stability and Redirects - 100/100

- Question: Can an agent trust that URLs will stay predictable?
- Category focus: Checks for stable docs URLs and minimal redirect churn on core paths.
- Category note: This area is already one of the stronger parts of the report.
- Passed: 2
- Warnings: 0
- Failed: 0
- Skipped: 0

Checks:
- PASS - Http Status Codes: All 10 sampled pages return proper error codes for bad URLs
- PASS - Redirect Behavior: No redirects detected across 10 sampled pages

### Authentication and Access - 100/100

- Question: Can an agent access the docs without getting blocked?
- Category focus: Checks whether public docs stay accessible and auth-gated content is handled clearly.
- Category note: 1 check were skipped in this report.
- Passed: 1
- Warnings: 0
- Failed: 0
- Skipped: 1

Checks:
- PASS - Auth Gate Detection: All 10 sampled pages are publicly accessible
- SKIP - Auth Alternative Access: All docs pages are publicly accessible; no alternative access paths needed

### Content Structure - 100/100

- Question: Can an agent understand how the page is organized?
- Category focus: Checks for headings, code block formatting, and readable section hierarchy.
- Category note: This area is already one of the stronger parts of the report.
- Passed: 3
- Warnings: 0
- Failed: 0
- Skipped: 0

Checks:
- PASS - Tabbed Content Serialization: No tabbed content detected across 10 sampled pages
- PASS - Section Header Quality: No tabbed content found; header quality check not applicable
- PASS - Markdown Code Fence Validity: All 54 code fences properly closed across 11 pages

### Markdown Availability - 100/100

- Question: Can an agent fetch a clean text version of the docs?
- Category focus: Checks for markdown routes and clean text delivery without UI-heavy wrappers.
- Category note: This area is already one of the stronger parts of the report.
- Passed: 2
- Warnings: 0
- Failed: 0
- Skipped: 0

Checks:
- PASS - Markdown Url Support: 9/9 sampled pages support .md URLs (100%)
- PASS - Content Negotiation: 9/9 sampled pages support content negotiation (100%)

### Content Discoverability - 88/100

- Question: Can an agent find the right starting point?
- Category focus: Checks for llms.txt, sitemaps, and a clear public docs entry point.
- Category note: 3 warnings still need cleanup here.
- Passed: 3
- Warnings: 3
- Failed: 0
- Skipped: 0

Checks:
- PASS - LLMS TXT Exists: llms.txt found at 2 location(s)
- WARN - LLMS TXT Valid: llms.txt contains parseable links but doesn't fully follow the proposed structure: https://developers.deepgram.com/docs/llms.txt: No blockquote summary found, No heading-delimited sections found, No markdown links found; https://developers.deepgram.com/llms.txt: No blockquote summary found
- WARN - LLMS TXT Size: llms.txt is 56,951 characters (between 50,000 and 100,000; consider splitting)
- PASS - LLMS TXT Links Resolve: All 10 same-origin sampled links resolve (309 total links)
- PASS - LLMS TXT Links Markdown: 10/10 same-origin sampled links point to markdown content (100%)
- WARN - LLMS TXT Directive (HTML): llms.txt directive found in 9 of 10 sampled pages (1 missing)


## Suggested Handoff

Ask the developer or coding agent to work through the failed checks and next-step items first, then rerun the benchmark on https://developers.deepgram.com/docs to confirm the score moves in the right direction.