Skip to content

Benchmark

FinBen BigData22 Acc

Scores are percentages. Higher is better.

Models measured
19
Scores recorded
19
Sources
1
IQ weight
0.00

Score distribution

52.4%
Mean
54%
Median
3.6%
Std dev
46.7%
10th percentile
55.2%
90th percentile
45%
Min
45%56.3%
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 19 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1codellama-7bpublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results56.3%
2Qwen 2 (72B)published-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results56%
3Qwen2.5 7Bpublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results55.2%
4Mistral (7B) Instruct v0.3published-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results55%
5gemini-1.0-propublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results55%
6Qwen2 7B Instructpublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results55%
7DeepSeek R1 Distill Qwen 1.5Bpublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results54.9%
8DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results54.9%
9GPT-4 Turbopublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results54%
10Llama 3.1 8Bpublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results54%
11Llama-2-7b-chat-hfpublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results54%
12DeepSeek V3published-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results53.1%
13GPT-3.5 Turbopublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results53%
14code-llama-7b-instructpublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results50.6%
15Qwen2.5 7B Instructpublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results49.9%
16Llama 2 70bpublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results47%
17Llama 3.2 3Bpublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results46.7%
18Mixtral 8X7b V0.1published-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results46%
19Llama 3.1 70Bpublished-demo-leaderboard, BigData22, Acc· TheFinAI public numeric results45%

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.