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 DeepPlanning value for, ranked by that value.
A long-horizon planning benchmark that tests whether agents can optimize under explicit time, budget, and feasibility constraints. 7 models in the ModelScale catalog have a published value.
Each point is a model with a published DeepPlanning value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
7 models with a published DeepPlanning 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 | Long-horizon planning benchmark |
|---|---|---|---|
| 1 | Alibaba | 62.3 | |
| 2 | Alibaba | 41.5 | |
| 3 | Alibaba | 37.6 |
What the benchmark measures and how its value is published, from the source’s own record.
DeepPlanning is an agentic benchmark published by DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints. A long-horizon planning benchmark that tests whether agents can optimize under explicit time, budget, and feasibility constraints. Its evaluation set is described by the source as travel planning and constrained shopping. The source rates its difficulty as constrained agent planning.
Each model's result is published by DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints as long-horizon planning benchmark. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 7 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.
| 4 | Anthropic | 26.4 |
| 5 | Alibaba | 25.9 |
| 6 | Z.AI | 14.6 |
| 7 | Moonshot AI | 14.4 |
Evidence key: Observed
Rows are ordered by the value DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints 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.