textFujitsu-FRE/MAPSagentsbenchmarkmultilingualevaluationsecuritygaiaswe-benchmathagentic-aisafety
MAPS: Multilingual Agentic AI Benchmark (Performance & Security)
About this data
805-task multilingual benchmark for evaluating agentic AI across 11 languages, combining performance tasks (GAIA, SWE-bench, MATH) with Agent Security Benchmark tasks. CC-BY-4.0.
Schema
| Name | Type | Description |
|---|---|---|
| task_id | VARCHAR | UUID string uniquely identifying each task in the benchmark |
| Question | VARCHAR | Task instruction or query in target language requiring agent completion |
| Level | VARCHAR | Difficulty rating (1-3) indicating task complexity |
| Final answer | VARCHAR | Ground-truth answer or expected output for task evaluation |
| file_name | VARCHAR | Original filename of the task source document or resource |
| file_path | VARCHAR | File path or URL reference to the source document or resource |
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: "MAPS: Multilingual Agentic AI " })
// Found: 5deeba74-7914-4cce-81f5-ad60f86f7a74
get_download_url({ dataset_id: "5deeba74-7914-4cce-81f5-ad60f86f7a74" }) // free — no API key neededVia REST API
# Free dataset — no API key required: curl https://api.databazaar.io/datasets/5deeba74-7914-4cce-81f5-ad60f86f7a74/download-url