ByteDance-Seed/WideSearch
WideSearch: Benchmarking Agentic Broad Info-Seeking
WideSearch helps you automate large-scale, repetitive information gathering tasks that are often overwhelming due to sheer volume, not complexity. It takes a broad information-seeking goal (like 'all financial metrics for a sector') and produces structured, organized output, freeing up human workers from tedious data collection. This is ideal for analysts, researchers, or anyone needing comprehensive datasets from disparate sources.
127 stars. No commits in the last 6 months.
Use this if you need to systematically collect and organize extensive information, where the main challenge is the volume and repetition of data gathering.
Not ideal if your primary challenge is finding very obscure facts or synthesizing complex reports from already found information.
Stars
127
Forks
12
Language
Python
License
MIT
Category
Last pushed
Oct 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ByteDance-Seed/WideSearch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
sierra-research/tau2-bench
τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment
xlang-ai/OSWorld
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
bigcode-project/bigcodebench
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
THUDM/AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
scicode-bench/SciCode
A benchmark that challenges language models to code solutions for scientific problems