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.
Coding benchmark
Every model the catalog carries a published FrontierSWE value for, ranked by that value.
An ultra-long-horizon software-engineering benchmark with open-ended implementation, performance, and research tasks designed to challenge frontier coding agents. 3 models in the ModelScale catalog have a published value.
Each point is a model with a published FrontierSWE value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
3 models with a published FrontierSWE 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 | Mean@5, best@5, average rank, and dominance |
|---|---|---|---|
| 1 | Moonshot AI | 81.2 | |
| 2 | Z.AI | 78.1 | |
| 3 | Alibaba | 73.5 |
Evidence key: Observed
What the benchmark measures and how its value is published, from the source’s own record.
FrontierSWE is a coding benchmark published by FrontierSWE: Benchmarking coding agents at the limits of human abilities. An ultra-long-horizon software-engineering benchmark with open-ended implementation, performance, and research tasks designed to challenge frontier coding agents. Its evaluation set is described by the source as 17 ultra-long-horizon engineering and research tasks. The source rates its difficulty as ultra-long-horizon frontier software engineering.
Each model's result is published by FrontierSWE: Benchmarking coding agents at the limits of human abilities as mean@5, best@5, average rank, and dominance. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 3 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.
Rows are ordered by the value FrontierSWE: Benchmarking coding agents at the limits of human abilities 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.