Skip to content

Benchmark

FinBen EFP Macro F1

Scores are percentages. Higher is better.

Models measured
6
Scores recorded
6
Sources
1
IQ weight
0.67

Score distribution

17.7%
Mean
14.2%
Median
6.5%
Std dev
14.2%
10th percentile
32%
90th percentile
14.2%
Min
14.2%32%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.67 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen2.5 7Bpublished-demo-leaderboard, EFP, Macro F1· TheFinAI public numeric results32%
2code-llama-7b-instructpublished-demo-leaderboard, EFP, Macro F1· TheFinAI public numeric results17.3%
3codellama-7bpublished-demo-leaderboard, EFP, Macro F1· TheFinAI public numeric results14.2%
4Llama 3.2 3Bpublished-demo-leaderboard, EFP, Macro F1· TheFinAI public numeric results14.2%
5Mistral (7B) Instruct v0.3published-demo-leaderboard, EFP, Macro F1· TheFinAI public numeric results14.2%
6Qwen2.5 7B Instructpublished-demo-leaderboard, EFP, Macro F1· TheFinAI public numeric results14.2%

Data credits: The Fin AI. Published FinBen result summaries and Open Greek Financial LLM Leaderboard aggregates. Results licence not separately stated; fractional FinBen success metrics converted to percentages.