How LlamaParse’s scores are calculated
The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.
verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10
PA Score33/100
Agent-ready 63.3 × 0.30 = 18.99
API quality 5.1 × 0.20 = 1.02
Openness 39.0 × 0.20 = 7.80
Built-in AI 13.3 × 0.15 = 2.00
Automation 18.0 × 0.15 = 2.70
(18.99 + 1.02 + 7.80 + 2.00 + 2.70) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 32.51 ÷ 1.00 = 32.5
Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.
Agent-ready63.3/100×0.30 of the PA blend
Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.
Point an agent at llms.txt or agent-oriented docsweight 2
2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max
- [probe] https://developers.llamaindex.ai/llms.txt“PROBE llms.txt: HTTP 200 at https://developers.llamaindex.ai/llms.txt # LlamaIndex Documentation > LlamaIndex is a framework for building LLM-powered applications over your data. It support”
- [claimed-docs] https://developers.llamaindex.ai/for-agents/“My agent should be able to search these docs”
- [claimed-docs] https://developers.llamaindex.ai/for-agents/mcp/“The server ships with the following tools: 1. `search_docs` — a basic lexical search using BM25 2. `grep_docs` — exact search using regex 3. `read_doc` — provides an interface to read the entire contents of any given page path”
- [claimed-docs] https://developers.llamaindex.ai/for-agents/mcp/“search_docs — a basic lexical search using BM25 2. grep_docs — exact search using regex 3. read_doc — provides an interface to read the entire contents of any given page path”
- [probe] https://developers.llamaindex.ai/for-agents/mcp/“official MCP server documented at https://developers.llamaindex.ai/for-agents/mcp/”
- [probe] https://developers.llamaindex.ai/llamaparse/.md“PROBE docs-md: HTTP 404 at https://developers.llamaindex.ai/llamaparse/.md”
Run the product headlessly / in CI for automationweight 2
2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“Get your first parse job running in under a minute—whether you prefer Python, TypeScript, Go, Java, the CLI, the REST API, or the Web UI.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/general/webhooks/“Instead of continuously polling for status updates, you can configure webhook endpoints to be notified immediately when jobs complete, fail, or reach other states.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“result = client.parsing.parse( file_id=file.id, tier="agentic", version="latest", expand=["markdown"],)”
Plug MCP servers into this product so it can use their toolsweight 3
n/a — not applicable to this product: excluded from numerator and denominator
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Connect an agent via an official MCP serverweight 3
3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max
- [claimed-docs] https://developers.llamaindex.ai/for-agents/“https://mcp.llamaindex.ai/mcp is the endpoint that exposes the platform's document processing — Parse, Classify, Extract, Split, and Index — as tools any MCP client can call.”
- [claimed-docs] https://developers.llamaindex.ai/for-agents/“`https://mcp.llamaindex.ai/mcp` is the endpoint that exposes the platform's document processing — Parse, Classify, Extract, Split, and Index — as tools any MCP client can call.”
- [probe] https://developers.llamaindex.ai/for-agents/mcp/“official MCP server documented at https://developers.llamaindex.ai/for-agents/mcp/”
- [claimed-docs] https://developers.llamaindex.ai/for-agents/mcp/“The server ships with the following tools: 1. `search_docs` — a basic lexical search using BM25 2. `grep_docs` — exact search using regex 3. `read_doc` — provides an interface to read the entire contents of any given page path”
Use an official CLIweight 2
2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“Get your first parse job running in under a minute—whether you prefer Python, TypeScript, Go, Java, the CLI, the REST API, or the Web UI.”
Drive the product through a documented public APIweight 3
3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“Get your first parse job running in under a minute—whether you prefer Python, TypeScript, Go, Java, the CLI, the REST API, or the Web UI.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“result = client.parsing.parse( file_id=file.id, tier="agentic", version="latest", expand=["markdown"],)”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/general/webhooks/“Instead of continuously polling for status updates, you can configure webhook endpoints to be notified immediately when jobs complete, fail, or reach other states.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/“One API key, one SDK, and five composable products: Parse (agentic OCR), Extract (structured data), Classify, Split, and Index.”
- [probe] https://developers.llamaindex.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://developers.llamaindex.ai/openapi.json, https://developers.llamaindex.ai/swagger.json, https://developers.llamaindex.ai/api/openapi.json, https://developers.llamaindex.ai/.well-known/openapi.json)”
Issue scoped/least-privilege API credentials for an agentweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/“Identity and access. Use SSO and role-based access controls to manage access to your organization and projects.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/“Use SSO and role-based access controls to manage access to your organization and projects.”
Build against official SDKsweight 2
2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“Get your first parse job running in under a minute—whether you prefer Python, TypeScript, Go, Java, the CLI, the REST API, or the Web UI.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“result = client.parsing.parse( file_id=file.id, tier="agentic", version="latest", expand=["markdown"],)”
- [github] https://github.com/run-llama/llama_cloud_services“Please migrate to the new packages: - **Python**: `pip install llama-cloud>=1.0`”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/“One API key, one SDK, and five composable products: Parse (agentic OCR), Extract (structured data), Classify, Split, and Index.”
Subscribe to events via webhooksweight 2
2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/general/webhooks/“Instead of continuously polling for status updates, you can configure webhook endpoints to be notified immediately when jobs complete, fail, or reach other states.”
Agent-ready = 114.0 ÷ 180 × 100 = 63.3
API quality5.1/100×0.20 of the PA blend
The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.
Explore an interactive API reference with runnable examplesweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [probe] https://developers.llamaindex.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://developers.llamaindex.ai/openapi.json, https://developers.llamaindex.ai/swagger.json, https://developers.llamaindex.ai/api/openapi.json, https://developers.llamaindex.ai/.well-known/openapi.json)”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“result = client.parsing.parse( file_id=file.id, tier="agentic", version="latest", expand=["markdown"],)”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/examples/“pull every table out into pandas DataFrames with source-page provenance, and turn on Cost Optimizer to keep costs down on long mixed-complexity documents”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/v1/examples/“Guide parsing output with custom prompts. Extract specific data from a McDonald's receipt by instructing the parser to focus only on prices and totals.”
Download a machine-readable API spec (OpenAPI or equivalent)weight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [probe] https://developers.llamaindex.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://developers.llamaindex.ai/openapi.json, https://developers.llamaindex.ai/swagger.json, https://developers.llamaindex.ai/api/openapi.json, https://developers.llamaindex.ai/.well-known/openapi.json)”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“Get your first parse job running in under a minute—whether you prefer Python, TypeScript, Go, Java, the CLI, the REST API, or the Web UI.”
Test against a sandbox environment without touching production dataweight 1
1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Rely on versioned APIs with a documented deprecation policyweight 2
2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“result = client.parsing.parse( file_id=file.id, tier="agentic", version="latest", expand=["markdown"],)”
- [github] https://github.com/run-llama/llama_cloud_services“Please migrate to the new packages: - **Python**: `pip install llama-cloud>=1.0`”
API quality = 3.6 ÷ 70 × 100 = 5.1
Openness39.0/100×0.20 of the PA blend
Can you leave, inspect, or self-host — data export, open source, portability.
Do everything through the API that I can do in the UIweight 2
2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“Get your first parse job running in under a minute—whether you prefer Python, TypeScript, Go, Java, the CLI, the REST API, or the Web UI.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/general/webhooks/“Instead of continuously polling for status updates, you can configure webhook endpoints to be notified immediately when jobs complete, fail, or reach other states.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/“Identity and access. Use SSO and role-based access controls to manage access to your organization and projects.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/extract/“Just define your Extraction Configuration (schema and settings), drag and drop any supported document into LlamaParse and extract data from your documents.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/“One API key, one SDK, and five composable products: Parse (agentic OCR), Extract (structured data), Classify, Split, and Index.”
- [probe] https://developers.llamaindex.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://developers.llamaindex.ai/openapi.json, https://developers.llamaindex.ai/swagger.json, https://developers.llamaindex.ai/api/openapi.json, https://developers.llamaindex.ai/.well-known/openapi.json)”
Export all of my data in open formats and leaveweight 3
3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/“Parse is an agentic document parser built for LLM pipelines—layout-aware OCR that turns PDFs, scans, tables, and charts into clean markdown, text, or JSON.”
- [claimed-docs] https://www.llamaindex.ai/llamaparse“Turn even the most complex layouts, tables, charts, handwriting, checkboxes, and images into clean markdown”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/self_hosting/“LlamaCloud can be deployed entirely within your own infrastructure. Self-hosted deployments — also known as BYOC (Bring Your Own Cloud) — give you the full capabilities of the LlamaCloud platform while keeping your data, models, and infrastructure under your control.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/self_hosting/“LlamaCloud can be deployed entirely within your own infrastructure... give you the full capabilities of the LlamaCloud platform while keeping your data, models, and infrastructure under your control.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/self_hosting/“Deploy LlamaCloud in your own cloud infrastructure with full self-hosting and BYOC support. Run LlamaParse, LlamaExtract, and the complete LlamaCloud platform on Kubernetes using Helm charts — on AWS, Azure, or GCP.”
Read the product's source under an open licenseweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [github] https://github.com/run-llama/llama_cloud_services“Please migrate to the new packages: - **Python**: `pip install llama-cloud>=1.0`”
Self-host the core productweight 3
3 (weight) × 7 (quality) × 1.0 (full) = 21.0 of 30 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/self_hosting/“LlamaCloud can be deployed entirely within your own infrastructure. Self-hosted deployments — also known as BYOC (Bring Your Own Cloud) — give you the full capabilities of the LlamaCloud platform while keeping your data, models, and infrastructure under your control.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/self_hosting/“LlamaCloud can be deployed entirely within your own infrastructure... give you the full capabilities of the LlamaCloud platform while keeping your data, models, and infrastructure under your control.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/self_hosting/“Deploy LlamaCloud in your own cloud infrastructure with full self-hosting and BYOC support. Run LlamaParse, LlamaExtract, and the complete LlamaCloud platform on Kubernetes using Helm charts — on AWS, Azure, or GCP.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/“Enterprise readiness, deployment & data residency: "managed SaaS, single-tenant, BYOC, self-hosting, and regional endpoints" — the platform documents self-hosting and regional deployment options alongside the managed cloud.”
Openness = 39.0 ÷ 100 × 100 = 39.0
Built-in AI13.3/100×0.15 of the PA blend
Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.
Get AI-generated insights and suggestions from my data inside the productweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/extract/“LlamaExtract provides a simple API for extracting structured data from unstructured documents like PDFs, text files, and images.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/extract/“Just define your Extraction Configuration (schema and settings), drag and drop any supported document into LlamaParse and extract data from your documents.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/extract/examples/“Generate extraction schemas with a prompt”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/“One API key, one SDK, and five composable products: Parse (agentic OCR), Extract (structured data), Classify, Split, and Index.”
Set up automations that run autonomously in the backgroundweight 2
2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/general/webhooks/“Instead of continuously polling for status updates, you can configure webhook endpoints to be notified immediately when jobs complete, fail, or reach other states.”
- [claimed-docs] https://developers.llamaindex.ai/for-agents/“https://mcp.llamaindex.ai/mcp is the endpoint that exposes the platform's document processing — Parse, Classify, Extract, Split, and Index — as tools any MCP client can call.”
- [claimed-docs] https://developers.llamaindex.ai/for-agents/“`https://mcp.llamaindex.ai/mcp` is the endpoint that exposes the platform's document processing — Parse, Classify, Extract, Split, and Index — as tools any MCP client can call.”
- [probe] https://developers.llamaindex.ai/for-agents/mcp/“official MCP server documented at https://developers.llamaindex.ai/for-agents/mcp/”
Delegate tasks to a built-in AI assistant inside the productweight 3
3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Operate the product with natural-language commandsweight 2
2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/classify/“Classify lets you automatically categorize documents into types you define (for example: invoice, receipt, contract) using natural-language rules.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/extract/examples/“Generate extraction schemas with a prompt”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/v1/examples/“Guide parsing output with custom prompts. Extract specific data from a McDonald's receipt by instructing the parser to focus only on prices and totals.”
- [claimed-docs] https://developers.llamaindex.ai/for-agents/“https://mcp.llamaindex.ai/mcp is the endpoint that exposes the platform's document processing — Parse, Classify, Extract, Split, and Index — as tools any MCP client can call.”
- [claimed-docs] https://developers.llamaindex.ai/for-agents/“`https://mcp.llamaindex.ai/mcp` is the endpoint that exposes the platform's document processing — Parse, Classify, Extract, Split, and Index — as tools any MCP client can call.”
Built-in AI = 12.0 ÷ 90 × 100 = 13.3
Automation18.0/100×0.15 of the PA blend
Depth of automation primitives — rules, scheduling, bulk operations, webhooks.
Perform bulk operations across many items at onceweight 2
2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/general/webhooks/“Instead of continuously polling for status updates, you can configure webhook endpoints to be notified immediately when jobs complete, fail, or reach other states.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/classify/examples/“Save reusable classification rules as a configuration and reference them by ID across multiple jobs.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“Get your first parse job running in under a minute—whether you prefer Python, TypeScript, Go, Java, the CLI, the REST API, or the Web UI.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/parse/getting_started/“result = client.parsing.parse( file_id=file.id, tier="agentic", version="latest", expand=["markdown"],)”
Define rules that trigger actions automatically on eventsweight 3
3 (weight) × 4 (quality) × 0.6 (partial) = 7.2 of 30 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/general/webhooks/“Instead of continuously polling for status updates, you can configure webhook endpoints to be notified immediately when jobs complete, fail, or reach other states.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/classify/examples/“Save reusable classification rules as a configuration and reference them by ID across multiple jobs.”
Schedule recurring jobs or workflowsweight 2
2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/general/webhooks/“Instead of continuously polling for status updates, you can configure webhook endpoints to be notified immediately when jobs complete, fail, or reach other states.”
- [claimed-docs] https://developers.llamaindex.ai/llamaparse/“One API key, one SDK, and five composable products: Parse (agentic OCR), Extract (structured data), Classify, Split, and Index.”
Version, review, and roll back my automationsweight 1
1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max
no evidence cited — the verdict rests on absence of evidence, re-checked on refresh
Automation = 14.4 ÷ 80 × 100 = 18.0