reasoning benchmark
Big Finance Bench
Big Finance Bench evaluates models on complex financial-analysis tasks that require retrieving and reasoning over financial documents and performing multi-step quantitative work.
Updated Aug 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
Big Finance Bench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | OP | 53.0% | 100.0% | 3 | C | |
| 2 | OP | 51.0% | 50.0% | 3 | C | |
| 3 | OP | 36.0% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
Big Finance Bench highlights
The top published results on this benchmark's own scale.
What is Big Finance Bench?
Definition and scoring fields from the benchmark registry.
Big Finance Bench evaluates models on complex financial-analysis tasks that require retrieving and reasoning over financial documents and performing multi-step quantitative work.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Big Finance Bench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- big-finance-bench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Big Finance Bench.
Which model scores highest on Big Finance Bench?
GPT-5.6 Sol is currently ranked first with 53.0%.
What does Big Finance Bench measure?
Big Finance Bench evaluates models on complex financial-analysis tasks that require retrieving and reasoning over financial documents and performing multi-step quantitative work.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 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.