Skip to content

Benchmark

FinBen EFP F1

Scores are percentages. Higher is better.

Models measured
13
Scores recorded
13
Sources
1
IQ weight
0.89

Score distribution

16.8%
Mean
12%
Median
10.4%
Std dev
11.5%
10th percentile
32.3%
90th percentile
11.5%
Min
11.5%47%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.89 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
1GPT-3.5 Turbopublished-demo-leaderboard, EFP, F1· TheFinAI public numeric results47%
2Qwen2.5 7Bpublished-demo-leaderboard, EFP, F1· TheFinAI public numeric results32.3%
3GPT-4 Turbopublished-demo-leaderboard, EFP, F1· TheFinAI public numeric results19%
4code-llama-7b-instructpublished-demo-leaderboard, EFP, F1· TheFinAI public numeric results15.6%
5Llama-2-7b-chat-hfpublished-demo-leaderboard, EFP, F1· TheFinAI public numeric results12%
6Mixtral 8X7b V0.1published-demo-leaderboard, EFP, F1· TheFinAI public numeric results12%
7Qwen2 7B Instructpublished-demo-leaderboard, EFP, F1· TheFinAI public numeric results12%
8codellama-7bpublished-demo-leaderboard, EFP, F1· TheFinAI public numeric results11.5%
9DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, EFP, F1· TheFinAI public numeric results11.5%
10DeepSeek V3published-demo-leaderboard, EFP, F1· TheFinAI public numeric results11.5%
11Llama 3.2 3Bpublished-demo-leaderboard, EFP, F1· TheFinAI public numeric results11.5%
12Mistral (7B) Instruct v0.3published-demo-leaderboard, EFP, F1· TheFinAI public numeric results11.5%
13Qwen2.5 7B Instructpublished-demo-leaderboard, EFP, F1· TheFinAI public numeric results11.5%

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.