textgoogle/deepsearchqabenchmarkagentsdeep-researchfactualityquestion-answeringretrievalgoogle-deepmindevalragapache-2.0

DeepSearchQA — Google DeepMind 900-Prompt Agent Factuality Benchmark

Name: DeepSearchQA — Google DeepMind 900-Prompt Agent Factuality Benchmark
Creator: DataBazaar
Keywords: google/deepsearchqa, benchmark, agents, deep-research, factuality, question-answering, retrieval, google-deepmind, eval, rag, apache-2.0

About this data

900-prompt benchmark from Google DeepMind for evaluating agents on difficult multi-step information-seeking tasks across 17 fields. Apache-2.0, CSV format.

Schema

Name	Type	Description
problem	VARCHAR	Multi-step information-seeking question requiring comprehensive research and synthesis across multiple sources.
problem_category	VARCHAR	One of 17 subject domains (e.g., Politics & Government, Media & Entertainment).
answer	VARCHAR	Ground-truth factual answer to the problem; format varies by answer_type.
answer_type	VARCHAR	Answer format category: 'Single Answer', 'Set Answer', or other structured response types.

Sample Data

Preview a sample of the data before downloading.

Free

Open dataset

Quality: No ratings

0 downloads

Seller: DataBazaar

Agent? No sign-up needed →

For AI Agents

Via MCP Server

# 1. Add to your agent's MCP config (claude_desktop_config.json or similar):
{
  "mcpServers": {
    "databazaar": { "command": "npx", "args": ["databazaar-mcp"] }
  }
}

# 2. Your agent can then call:
search_datasets({ query: "DeepSearchQA — Google DeepMind" })
// Found: 24cf80b3-5f47-4da6-a6a5-0540b3688343
get_download_url({ dataset_id: "24cf80b3-5f47-4da6-a6a5-0540b3688343" })  // free — no API key needed

Via REST API

# Free dataset — no API key required:
curl https://api.databazaar.io/datasets/24cf80b3-5f47-4da6-a6a5-0540b3688343/download-url