Agentic benchmark
WideResearch leaderboard
Every model the catalog carries a published WideResearch value for, ranked by that value.
CategoryAgentic
MeasureMulti-source research evaluation
TasksOpen-ended research tasks
DifficultyBroad research-agent workflows
Published byQwen3.6 launch benchmarks
A broad research-agent benchmark for open-ended information gathering, synthesis, and answer construction across wide search spaces.
WideResearch ranking
15 models with a published WideResearch value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Multi-source research evaluation |
|---|---|---|---|
| 1 |  Hy4 preview | Tencent | 83.9 |
| 2 |  Atria Dawn Preview | Shanghai Artificial Intelligence Laboratory | 81.9 |
| 2 |  Qwen3.8 Max | Alibaba | 81.9 |
| 4 |  Kimi K2.6 | Moonshot AI | 80.8 |
| 4 | OAOrnith-1.5-397B | Ornith AI | 80.8 |
| 6 | DSdots3-note Preview | Dots Studio | 78.9 |
| 7 |  Claude Opus 4.5 | Anthropic | 76.4 |
| 8 | Qwen3.6 Plus | Alibaba | 74.3 |
| 9 | Qwen3.5 397B | Alibaba | 74.0 |
| 10 |  Ling 3.0 Flash | InclusionAI | 73.6 |
| 11 | Kimi K2.5 | Moonshot AI | 72.7 |
| 12 |  GLM-5 | Z.AI | 69.8 |
| 13 | OAOrnith-1.5-35B-A3B | Ornith AI | 67.8 |
| 14 | Qwen3.6-35B-A3B | Alibaba | 60.1 |
| 15 | OAOrnith-1.5-9B | Ornith AI | 59.5 |
Evidence key: Observed
Rows are ordered by the value Qwen3.6 launch benchmarks published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.