Benchmark
WideSearch Benchmark
What is WideSearch?
Wide-coverage web collection; scored on completeness of an enumerated answer set. Benchmark Radar tracks 2 reported scores for WideSearch, cited by 2 source…
- Released
- 2025-08-11
- Evaluates
- agent
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 2
Source provenance
- Original evidence https://widesearch-seed.github.io/
WideSearch links
WideSearch results and reported scores
Model reports
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.
Which sources cite WideSearch?
- Hy4 preview Tencent, 2026-08-28
- Qwen3.5-397B-A17B Qwen, 2026-02-16