math benchmark
FinQA Leaderboard
FinQA is a dataset for numerical reasoning over financial data, featuring question-answering pairs written by financial experts and annotated gold reasoning programs.
Updated Sep 5, 2026
Models3
Model coverage3
MetricScore
EvidenceB
FinQA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAM Nova ProAmazon | Score77.20% | Percentile100.00% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelAMNova LiteAmazon | Score73.60% | Percentile50.00% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelAMNova MicroAmazon | Score65.20% | Percentile0.00% | Participants3 | EvidenceC | Evaluated |
FinQA Highlights
The leading models and scores on this benchmark.
FinQA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for FinQA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is FinQA?
What FinQA measures and how its scores work.
FinQA is a dataset of financial question-answering pairs involving numerical reasoning and heterogeneous representations.
It measures numerical reasoning over financial data using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- FinQA
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about FinQA.
Which model scores highest on FinQA?
Nova Pro is currently ranked first with 77.20%.
What are the top three models on FinQA?
The current leaders are Nova Pro (77.20%), Nova Lite (73.60%), and Nova Micro (65.20%).
Which FinQA model has the lowest official input price?
Nova Micro has the lowest matched official input price at $0.04 input / $0.14 output per 1M tokens.
Which models are fastest among FinQA results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.