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 Finance Agent v2 value for, ranked by that value.
Vals AI benchmark for realistic financial analyst agent tasks across qualitative analysis, quantitative analysis, market work, comparables, precedents, earnings, disclosure, and modeling. 10 models in the ModelChoice catalog have a published value.
Each point is a model with a published Finance Agent v2 value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
10 models with a published Finance Agent v2 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 score across repeated runs |
|---|---|---|---|
| 1 | 65.4 | ||
| 2 | 61.4 | ||
| 3 | InclusionAI | 59.8 |
What the benchmark measures and how its value is published, from the source’s own record.
Finance Agent v2 is an agentic benchmark published by Finance Agent v2. Vals AI benchmark for realistic financial analyst agent tasks across qualitative analysis, quantitative analysis, market work, comparables, precedents, earnings, disclosure, and modeling. Its evaluation set is described by the source as financial analyst task categories. The source rates its difficulty as professional expert-task agent workflow.
Each model's result is published by Finance Agent v2 as mean score across repeated runs. ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 10 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 | Meta | 59.1 |
| 5 | InclusionAI | 57.9 |
| 6 | 57.9 |
| 7 | Meta | 57.2 |
| 8 | Meta | 56.6 |
| 9 | Mistral | 54.7 |
| 10 | Anthropic | 53.9 |
Evidence key: Observed
Rows are ordered by the value Finance Agent v2 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.