Skip to content

Benchmark

FinBen EFPA MCC

Higher scores are better.

Models measured
6
Scores recorded
6
Sources
1
IQ weight
1.08

Score distribution

0.05
Mean
0.027
Median
0.101
Std dev
-0.003
10th percentile
0.271
90th percentile
-0.03
Min

This benchmark has a weight of 1.08 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, EFPA, MCC· TheFinAI public numeric results0.271
2code-llama-7b-instructpublished-demo-leaderboard, EFPA, MCC· TheFinAI public numeric results0.0364
3Mistral (7B) Instruct v0.3published-demo-leaderboard, EFPA, MCC· TheFinAI public numeric results0.0269
4Qwen2.5 7B Instructpublished-demo-leaderboard, EFPA, MCC· TheFinAI public numeric results0
5Llama 3.2 3Bpublished-demo-leaderboard, EFPA, MCC· TheFinAI public numeric results-0.003
6codellama-7bpublished-demo-leaderboard, EFPA, MCC· TheFinAI public numeric results-0.03

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.