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 DAYJOB value for, ranked by that value.
DAYJOB is Surge AI's test of long professional assignments: 80 finance tasks and 50 healthcare tasks that an agent must finish to an expert checklist. This is the combined 130-task board on Kaggle. 19 models in the ModelScale catalog have a published value.
Each point is a model with a published DAYJOB value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
19 models with a published DAYJOB 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 deliverables graded all-or-nothing against expert rubrics |
|---|---|---|---|
| 1 | Anthropic | 24.5 | |
| 2 | Anthropic | 21.7 | |
| 3 | 19.7 |
What the benchmark measures and how its value is published, from the source’s own record.
DAYJOB is an external benchmark published by BenchLM. DAYJOB is Surge AI's test of long professional assignments: 80 finance tasks and 50 healthcare tasks that an agent must finish to an expert checklist. This is the combined 130-task board on Kaggle. Its evaluation set is described by the source as 130 long-horizon tasks: 80 finance and 50 healthcare. The source rates its difficulty as long-horizon professional work.
Each model's result is published by BenchLM as agent deliverables graded all-or-nothing against expert rubrics. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 19 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 | OpenAI | 17.4 |
| 5 | 15.7 |
| 6 | OpenAI | 15.5 |
| 7 | Anthropic | 11.7 |
| 8 | OpenAI | 6.8 |
| 9 | OpenAI | 4.2 |
| 10 | OpenAI | 2.8 |
| 11 | 2.6 |
| 12 | Anthropic | 2.0 |
| 13 | Anthropic | 1.7 |
| 14 | OpenAI | 1.4 |
| 15 | OpenAI | 1.2 |
| 16 | OpenAI | 1.1 |
| 17 | 0.0 |
| 17 | 0.0 |
| 17 | 0.0 |
Evidence key: Observed
Rows are ordered by the value BenchLM 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.