> ## Content Index
> Fetch the complete content index at: https://serpapi.com/blog/llms.txt
> Use this file to discover other available public pages before exploring further.

# SerpApi Achieves 58.56% Accuracy on SEAL-0 and 66.93% on SEAL-Hard
- URL: https://serpapi.com/blog/serpapi-achieves-58-56-accuracy-on-seal-0-and-66-93-on-seal-hard/
- Published: 2026-11-06T10:58:32.000Z
- Updated: 2026-11-06T10:58:32.000Z
- Description: SerpApi achieved 58.56% accuracy on SEAL-0 and 66.93% on SEAL-Hard, pairing web search with page extraction to help an AI agent tackle tough factual questions.
- Author: Adarsh Divakaran
- Tags: evals, Search API, Extract API

We tested SerpApi’s Google Search and Extract APIs with GPT-6.1 Sol on SealQA, a benchmark built around factual questions that are difficult to resolve through web search.

The agent correctly answered **65 of 111 SEAL-0 questions**, achieving **58.56% accuracy**, and **170 of 254 SEAL-Hard questions**, achieving **66.93% accuracy**.

![](https://storage.ghost.io/c/a5/00/a5004977-0dd2-4bcd-9292-dd0e05d4c59e/content/images/2026/11/blog-image--5-.png)

[SealQA](https://arxiv.org/abs/2506.01062) tests how well models reason when search results contain conflicting, noisy, or unhelpful information. This makes it a useful benchmark for demanding agentic use cases, where high-quality search must surface the evidence needed to resolve contradictions, verify facts, and answer accurately.

SEAL-0 contains the benchmark’s hardest core questions. SEAL-Hard includes those same 111 questions plus 143 additional challenging questions.  
  
This follows our earlier evaluation, where SerpApi achieved 97.6% accuracy on SimpleQA Verified. 

[SerpApi Achieves 97.6% Accuracy on SimpleQA VerifiedSerpApi scored 97.6% on SimpleQA Verified. We tested Google search data and the Extract API to see how well they help AI agents answer factual questions.![](https://storage.ghost.io/c/a5/00/a5004977-0dd2-4bcd-9292-dd0e05d4c59e/content/images/icon/serpapi-favicon-57e42547-f4f9-4956-9fa4-7cca7db5f19f.png)SerpApiAdarsh Divakaran![](https://storage.ghost.io/c/a5/00/a5004977-0dd2-4bcd-9292-dd0e05d4c59e/content/images/thumbnail/download--5--e0712aa9-4666-4dbe-810b-1b4f2920f3be.png)](https://serpapi.com/blog/serpapi-achieves-97-6-accuracy-on-simpleqa-verified/)

These evaluations show how SerpApi’s Google Search and Extract APIs help agents tackle difficult questions by finding relevant sources, reading pages, cross-checking evidence, and making follow-up searches when the initial results leave gaps.

## How we tested Google Search and Extract for AI agents

We connected GPT-6.1 Sol, using medium reasoning, to SerpApi’s Google Search and Extract APIs.

The agent searched Google, read the returned evidence, and opened relevant pages when snippets were insufficient. It could make follow-up searches and compare sources before answering.

| Setting                | Configuration                                          |
| ---------------------- | ------------------------------------------------------ |
| Answer model           | GPT-6.1 Sol (gpt-6.1-sol), medium reasoning            |
| Search                 | SerpApi Google Search, engine=google                   |
| Search output          | Markdown, output=md                                    |
| Page content           | SerpApi's Extract API                                  |
| Search and tool limits | Up to 10 searches and 24 total tool calls per question |

### SERP data in Markdown

We used the [Google Search API](https://serpapi.com/search-api) with Markdown output. The model received useful search content, including organic results, answer boxes, and AI Overviews when available.

The eval harness lets the model read the result pages and make follow-up queries.

### Web page extraction with SerpApi Extract API

When search results did not provide enough evidence, the agent used the [Extract API](https://serpapi.com/extract-api.md) to read page content as Markdown.

The model could use this content to check details, resolve disagreements between sources, or identify a more specific search query. Fetched content was limited to 48,000 characters per page, with a maximum of 56,000 input tokens per model request.

### Grading and exclusions

The grader (GPT-5.6 Sol) evaluated each prediction against the reference answer using high reasoning and the official SealQA rubric, with search and other tools disabled.

Our exposure review found one search snippet from the benchmark paper that repeated a question without revealing its answer or additional solving guidance. We retained that case in the reported SEAL-Hard score. Conservatively excluding it gives **66.80%**, or **169 of 253 questions correct**.

## SEAL-0 and SEAL-Hard results

| Benchmark     | Questions | Correct answers | Accuracy   |
| ------------- | --------- | --------------- | ---------- |
| **SEAL-0**    | 111       | 65              | **58.56%** |
| **SEAL-Hard** | 254       | 170             | **66.93%** |

The higher SEAL-Hard score reflects the composition of the dataset: SEAL-0 is its more difficult subset. These are overlapping question sets, so the results cover **254 unique questions**.

These results make SerpApi a strong choice for adding web search to your AI agents. Together with our SimpleQA Verified result, they demonstrate strong accuracy across straightforward factual questions and more challenging tasks involving conflicting or incomplete evidence.

## What’s next?

Add SerpApi to your agents and give them access to live web search:

**Building a Python agent?** Use [SerpApi Search Tools](https://serpapi.github.io/serpapi-search-tools-python/) to add ready-to-use search tools to OpenAI Agents, LangChain, Pydantic AI, CrewAI, and other supported frameworks.

[Introducing SerpApi Search Tools: Real-Time Web Search for Python AI AgentsThe \`serpapi-search-tools\` package gives Python agents real-time access to the web, news, maps, images, shopping, YouTube, hotels, flights, and travel search, powered by SerpApi. It natively supports popular SDKs including LangChain, Agno, CrewAI, OpenAI Agents, Pydantic AI, Google ADK, and more.![](https://storage.ghost.io/c/a5/00/a5004977-0dd2-4bcd-9292-dd0e05d4c59e/content/images/icon/serpapi-favicon-9f205287-0232-4d87-b591-6f836c76c80e.png)SerpApiAdarsh Divakaran![](https://storage.ghost.io/c/a5/00/a5004977-0dd2-4bcd-9292-dd0e05d4c59e/content/images/thumbnail/download--4---2--82e553a4-6417-4c0f-8f56-d274bac4e519.png)](https://serpapi.com/blog/introducing-serpapi-search-tools-real-time-web-search-for-python-ai-agents/)

**Using an MCP-compatible client?** Connect our [MCP server](https://serpapi.com/integrations/mcp) to bring SerpApi search into Claude Desktop, Cursor, VS Code, and other AI tools.

[Introducing SerpApi’s MCP Server (Web Search MCP)Today, we are releasing an open-source Model Context Protocol (MCP) server that exposes our web search API to AI agents and developers through a familiar and common interface.![](https://storage.ghost.io/c/a5/00/a5004977-0dd2-4bcd-9292-dd0e05d4c59e/content/images/icon/serpapi-favicon-a597a079-2bd2-4d10-bf77-a7d0e0988e60.png)SerpApiJames Collins![](https://storage.ghost.io/c/a5/00/a5004977-0dd2-4bcd-9292-dd0e05d4c59e/content/images/thumbnail/blog-post-mcp-image-cec188a4-c0fa-4541-98b3-c4d2182cf818.jpg)](https://serpapi.com/blog/introducing-serpapis-mcp-server/)

Pair search with the [Extract API](https://serpapi.com/extract-api.md) when your agent needs to read the pages it finds.

[Introducing the SerpApi Extract API: Fetch and parse any web pageThe new Extract API turns any public web page into Markdown, ready for your application, AI agent, or other automation.![](https://storage.ghost.io/c/a5/00/a5004977-0dd2-4bcd-9292-dd0e05d4c59e/content/images/icon/serpapi-favicon-ef69e907-6faf-4a9c-b376-5a106f84f09f.png)SerpApiCorbin Davenport![](https://storage.ghost.io/c/a5/00/a5004977-0dd2-4bcd-9292-dd0e05d4c59e/content/images/thumbnail/mk-44bc669e-a581-4d8f-8109-35f10c80a34f.jpg)](https://serpapi.com/blog/introducing-extract-api/)