Skip to content

Benchmark

FinBen FinanceES ACC

Scores are percentages. Higher is better.

Models measured
13
Scores recorded
13
Sources
1
IQ weight
0.00

Score distribution

16.4%
Mean
14%
Median
5.1%
Std dev
12.3%
10th percentile
26.3%
90th percentile
11.2%
Min
11.2%28.4%
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
1DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, FinanceES, ACC· TheFinAI public numeric results28.4%
2Qwen2.5 7B Instructpublished-demo-leaderboard, FinanceES, Acc· TheFinAI public numeric results26.3%
3Mistral (7B) Instruct v0.3published-demo-leaderboard, FinanceES, Acc· TheFinAI public numeric results19.1%
4code-llama-7b-instructpublished-demo-leaderboard, FinanceES, Acc· TheFinAI public numeric results17.4%
5codellama-7bpublished-demo-leaderboard, FinanceES, Acc· TheFinAI public numeric results16.1%
6GPT-4 Turbopublished-demo-leaderboard, FinanceES, ACC· TheFinAI public numeric results15%
7Llama-2-7b-chat-hfpublished-demo-leaderboard, FinanceES, ACC· TheFinAI public numeric results14%
8Qwen2 7B Instructpublished-demo-leaderboard, FinanceES, ACC· TheFinAI public numeric results14%
9DeepSeek V3published-demo-leaderboard, FinanceES, ACC· TheFinAI public numeric results13.7%
10GPT-3.5 Turbopublished-demo-leaderboard, FinanceES, ACC· TheFinAI public numeric results13%
11Mixtral 8X7b V0.1published-demo-leaderboard, FinanceES, ACC· TheFinAI public numeric results13%
12Qwen2.5 7Bpublished-demo-leaderboard, FinanceES, Acc· TheFinAI public numeric results12.3%
13Llama 3.2 3Bpublished-demo-leaderboard, FinanceES, Acc· TheFinAI public numeric results11.2%

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.