Skip to content

Benchmark

FinBen EFPA F1

Scores are percentages. Higher is better.

Models measured
13
Scores recorded
13
Sources
1
IQ weight
1.41

Score distribution

15.6%
Mean
11.3%
Median
8.7%
Std dev
10.3%
10th percentile
27%
90th percentile
10%
Min
10%39.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.41 for chat models, measured over 13 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, F1· TheFinAI public numeric results39.3%
2GPT-4 Turbopublished-demo-leaderboard, EFPA, F1· TheFinAI public numeric results27%
3GPT-3.5 Turbopublished-demo-leaderboard, EFPA, F1· TheFinAI public numeric results25%
4Qwen2 7B Instructpublished-demo-leaderboard, EFPA, F1· TheFinAI public numeric results14%
5code-llama-7b-instructpublished-demo-leaderboard, EFPA, F1· TheFinAI public numeric results12.9%
6Mixtral 8X7b V0.1published-demo-leaderboard, EFPA, F1· TheFinAI public numeric results12%
7Mistral (7B) Instruct v0.3published-demo-leaderboard, EFPA, F1· TheFinAI public numeric results11.3%
8Llama 3.2 3Bpublished-demo-leaderboard, EFPA, F1· TheFinAI public numeric results10.4%
9codellama-7bpublished-demo-leaderboard, EFPA, F1· TheFinAI public numeric results10.3%
10DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, EFPA, F1· TheFinAI public numeric results10.3%
11DeepSeek V3published-demo-leaderboard, EFPA, F1· TheFinAI public numeric results10.3%
12Qwen2.5 7B Instructpublished-demo-leaderboard, EFPA, F1· TheFinAI public numeric results10.3%
13Llama-2-7b-chat-hfpublished-demo-leaderboard, EFPA, F1· TheFinAI public numeric results10%

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.