Skip to content

Benchmark

FinBen FinanceES F1

Scores are percentages. Higher is better.

Models measured
13
Scores recorded
13
Sources
1
IQ weight
0.00

Score distribution

15.7%
Mean
13%
Median
6.1%
Std dev
8.1%
10th percentile
26%
90th percentile
8%
Min
8%26.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.00 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 7B Instructpublished-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results26.7%
2DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results26%
3code-llama-7b-instructpublished-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results20.5%
4Mixtral 8X7b V0.1published-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results20%
5Mistral (7B) Instruct v0.3published-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results19.4%
6codellama-7bpublished-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results16.2%
7Llama-2-7b-chat-hfpublished-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results13%
8Qwen2 7B Instructpublished-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results13%
9Llama 3.2 3Bpublished-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results12%
10Qwen2.5 7Bpublished-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results11.7%
11GPT-4 Turbopublished-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results9%
12DeepSeek V3published-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results8.1%
13GPT-3.5 Turbopublished-demo-leaderboard, FinanceES, F1· TheFinAI public numeric results8%

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.