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.
external benchmark
Every model the catalog carries a published Epoch Automation Reports value for, ranked by that value.
Epoch Automation Reports runs AI agents on open-ended tasks taken from Epoch AI's own work, such as graphic design, data insights and AI data center research, and has human graders score the output against Epoch's internal standards. 6 models in the ModelScale catalog have a published value.
Each point is a model with a published Epoch Automation Reports value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
6 models with a published Epoch Automation Reports 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 | Agent harness at highest reasoning setting, human rubric grading |
|---|---|---|---|
| 1 | Anthropic | 64.4 | |
| 2 | xAI | 59.1 | |
| 3 | OpenAI | 55.5 |
What the benchmark measures and how its value is published, from the source’s own record.
Epoch Automation Reports is an external benchmark published by Epoch Automation Reports. Epoch Automation Reports runs AI agents on open-ended tasks taken from Epoch AI's own work, such as graphic design, data insights and AI data center research, and has human graders score the output against Epoch's internal standards. Its evaluation set is described by the source as 11 open-ended work tasks in five categories from Epoch AI's own work. The source rates its difficulty as open-ended professional research and design work.
Each model's result is published by Epoch Automation Reports as agent harness at highest reasoning setting, human rubric grading. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 6 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 | Alibaba | 53.0 |
| 5 | Moonshot AI | 52.4 |
| 6 | 42.3 |
Evidence key: ObservedLast good
Rows are ordered by the value Epoch Automation Reports 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.