WideSearch: leaderboard
Agentic search benchmark focused on broad, parallel information gathering, where agents must cover many sources and synthesize the findings.
Metric: Score (%). Source: llm-stats.com. Status: saturation imminent. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Hy4 preview | 83.9 |
| 2 | Qwen 3.8 Max | 81.9 |
| 3 | Kimi K2.6 | 80.8 |
| 4 | Kimi K2.5 | 79 |
| 5 | Hy3 | 76.4 |
| 6 | Qwen 3.6 Plus | 74.3 |
| 7 | Qwen 3.5 397B A17B | 74 |
| 8 | Qwen 3.5 27B | 61.1 |
| 9 | Qwen 3.5 122B A10B | 60.5 |
| 10 | Qwen 3.6 35B A3B | 60.1 |
| 11 | Qwen 3.5 35B A3B | 57.1 |
Interactive version: theaggregate.ai/benchmark?slug=widesearch · How It Works · Data refreshed daily, snapshot 2026-09-05.