Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Agentic benchmark
Every model the catalog carries a published WideResearch value for, ranked by that value.
A broad research-agent benchmark for open-ended information gathering, synthesis, and answer construction across wide search spaces. 16 models in the ModelChoice catalog have a published value.
Each point is a model with a published WideResearch value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
16 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 | Tencent | 83.9 | |
| 2 | InclusionAI | 83.3 | |
| 3 | Shanghai Artificial Intelligence Laboratory |
What the benchmark measures and how its value is published, from the source’s own record.
WideResearch is an agentic benchmark published by Qwen3.6 launch benchmarks. A broad research-agent benchmark for open-ended information gathering, synthesis, and answer construction across wide search spaces. Its evaluation set is described by the source as open-ended research tasks. The source rates its difficulty as broad research-agent workflows.
Each model's result is published by Qwen3.6 launch benchmarks as multi-source research evaluation. ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 16 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 3 | Alibaba | 81.9 |
| 5 | Moonshot AI | 80.8 |
| 5 | OAOrnith-1.5-397B | Ornith AI | 80.8 |
| 7 | DSdots3-note Preview | Dots Studio | 78.9 |
| 8 | Anthropic | 76.4 |
| 9 | Alibaba | 74.3 |
| 10 | Alibaba | 74.0 |
| 11 | InclusionAI | 73.6 |
| 12 | Moonshot AI | 72.7 |
| 13 | Z.AI | 69.8 |
| 14 | OAOrnith-1.5-35B-A3B | Ornith AI | 67.8 |
| 15 | Alibaba | 60.1 |
| 16 | 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.