reasoning benchmark
Finance Agent v2
Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.
Updated Aug 7, 2026
Published models26
Registry coverage26
MetricScore
EvidenceB
Finance Agent v2 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
Score distribution
Top published rows on the benchmark's original scale.
Finance Agent v2 highlights
The top published results on this benchmark's own scale.
What is Finance Agent v2?
Definition and scoring fields from the benchmark registry.
Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Finance Agent v2
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- finance-agent-v2|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Finance Agent v2.
Which model scores highest on Finance Agent v2?
Gemini 3.5 Flash is currently ranked first with 57.9%.
What does Finance Agent v2 measure?
Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
26 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.