Benchmark
WideSearch
Wide-coverage web collection; scored on completeness of an enumerated answer set.
- Released
- 2025-08-11
- Categories
- agent
- Openness
- unknown
- Source
- model_reports
- Reported scores
- 2
Reported scores
model_reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Hy4 preview | Tencent | 83.9 | 2026-08-28 | evidence |
| Qwen3.5-397B-A17B | Qwen | 74.0 | 2026-02-16 | evidence |
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.