Skip to content

Benchmark

FinBen FinanceES Macro F1

Scores are percentages. Higher is better.

Models measured
6
Scores recorded
6
Sources
1
IQ weight
0.49

Score distribution

18.1%
Mean
17.9%
Median
3.6%
Std dev
15.3%
10th percentile
25.2%
90th percentile
14.9%
Min
14.9%25.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.49 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 7B Instructpublished-demo-leaderboard, FinanceES, Macro F1· TheFinAI public numeric results25.2%
2Mistral (7B) Instruct v0.3published-demo-leaderboard, FinanceES, Macro F1· TheFinAI public numeric results19.7%
3codellama-7bpublished-demo-leaderboard, FinanceES, Macro F1· TheFinAI public numeric results17.9%
4code-llama-7b-instructpublished-demo-leaderboard, FinanceES, Macro F1· TheFinAI public numeric results15.9%
5Qwen2.5 7Bpublished-demo-leaderboard, FinanceES, Macro F1· TheFinAI public numeric results15.3%
6Llama 3.2 3Bpublished-demo-leaderboard, FinanceES, Macro F1· TheFinAI public numeric results14.9%

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.