Skip to content

Benchmark

FinBen ACL18 Acc

Scores are percentages. Higher is better.

Models measured
19
Scores recorded
19
Sources
1
IQ weight
0.00

Score distribution

50.9%
Mean
51%
Median
1.1%
Std dev
49.8%
10th percentile
52%
90th percentile
49%
Min
49%53.1%
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
1DeepSeek V3published-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results53.1%
2DeepSeek R1 Distill Qwen 1.5Bpublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results52.5%
3gemini-1.0-propublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results52%
4GPT-4 Turbopublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results52%
5Llama 3.1 8Bpublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results52%
6code-llama-7b-instructpublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results51.9%
7codellama-7bpublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results51.2%
8DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results51.2%
9Mistral (7B) Instruct v0.3published-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results51.1%
10Llama 2 70bpublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results51%
11Llama-2-7b-chat-hfpublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results51%
12Qwen2.5 7Bpublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results50.7%
13Qwen2.5 7B Instructpublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results50.3%
14GPT-3.5 Turbopublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results50%
15Qwen 2 (72B)published-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results50%
16Qwen2 7B Instructpublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results50%
17Llama 3.2 3Bpublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results49.8%
18Llama 3.1 70Bpublished-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results49%
19Mixtral 8X7b V0.1published-demo-leaderboard, ACL18, Acc· TheFinAI public numeric results49%

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.