Finance Benchmark

Frontier Finance

Finance agent benchmark evaluated with the official Finance Agent v2 harness.

Category

Finance

Score type

percent

Scale

100%

higher is better

Models tested

3

What is Frontier Finance?

Frontier Finance is a benchmark for professional finance and business tasks. The official description says: "Finance agent benchmark evaluated with the official Finance Agent v2 harness". Below we describe in simple words what benchmarks of this type generally examine.

What does it test?

Frontier Finance measures professional finance and business tasks. In detail, it checks:

  • domain-specific terminology, data and regulations
  • reasoning about financial documents, markets and products
  • real work-product quality rather than textbook recall
  • numeric correctness on financial computations

How to read the score

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: Finance agent benchmark evaluated with the official Finance Agent v2 harness.

Frequently asked questions

What is the Frontier Finance benchmark?

Frontier Finance is a benchmark for professional finance and business tasks. The official description says: 'Finance agent benchmark evaluated with the official Finance Agent v2 harness'. Below we describe in simple words what benchmarks of this type generally examine.

What does Frontier Finance test?

Frontier Finance mainly measures professional finance and business tasks. Concretely, it checks: domain-specific terminology, data and regulations; reasoning about financial documents, markets and products; real work-product quality rather than textbook recall.

How is the Frontier Finance score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get Frontier Finance data and scores?

The official source is https://huggingface.co/moonshotai/Kimi-K3.1-Pro. The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/frontier-finance/scores) or pull it directly from the Open LLM Radar API with any HTTP client.

Model scores 3 models tested

Reset
# Model Score Date Source Verified
1 Kimi K3.1 Pro
Moonshot AI
58.6%
07.11.2026 Report Verified
2 GLM-5.3
Zhipu AI
57.5%
07.11.2026 Kimi K3.1 Pro model card comparison column (max effort) https://huggingface.co/moonshotai/Kimi-K3.1-Pro Unverified
3 DeepSeek-V4.1-Flash-1017
DeepSeek
54.5%
07.11.2026 Kimi K3.1 Pro model card comparison column (max effort) https://huggingface.co/moonshotai/Kimi-K3.1-Pro Unverified

What now?

You've seen how models score on Frontier Finance — here's what to do next.