reasoning benchmark
Finance Agent
Finance Agent is a benchmark for evaluating AI models on agentic financial analysis tasks, testing their ability to process financial data, perform calculations, and generate accurate analyses across various financial domains.
Updated Aug 7, 2026
Published models8
Registry coverage8
MetricScore
EvidenceB
Finance Agent leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AN | 64.4% | 100.0% | 8 | C | |
| 2 | AN | 63.3% | 85.7% | 8 | C | |
| 3 | AN | 60.7% | 71.4% | 8 | C | |
| 4 | OP | 60.0% | 57.1% | 8 | C | |
| 5 | GO | 57.9% | 42.9% | 8 | C | |
| 6 | OP | 56.0% | 28.6% | 8 | C | |
| 7 | AN | 53.9% | 14.3% | 8 | C | |
| 8 | NV | 53.7% | 0.0% | 8 | C |
Score distribution
Top published rows on the benchmark's original scale.
Finance Agent highlights
The top published results on this benchmark's own scale.
What is Finance Agent?
Definition and scoring fields from the benchmark registry.
Finance Agent is a benchmark for evaluating AI models on agentic financial analysis tasks, testing their ability to process financial data, perform calculations, and generate accurate analyses across various financial domains.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Finance Agent
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- finance-agent|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.
Which model scores highest on Finance Agent?
Claude Opus 4.7 is currently ranked first with 64.4%.
What does Finance Agent measure?
Finance Agent is a benchmark for evaluating AI models on agentic financial analysis tasks, testing their ability to process financial data, perform calculations, and generate accurate analyses across various financial domains.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
8 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.