Skip to content

Benchmark

FinBen CIKM18 Acc

Scores are percentages. Higher is better.

Models measured
19
Scores recorded
19
Sources
1
IQ weight
0.00

Score distribution

53.4%
Mean
54%
Median
4.4%
Std dev
49%
10th percentile
57.5%
90th percentile
42%
Min
42%58.5%
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
1Qwen2.5 7Bpublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results58.5%
2DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results57.7%
3code-llama-7b-instructpublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results57.5%
4codellama-7bpublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results57.2%
5GPT-4 Turbopublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results57%
6Llama 3.1 8Bpublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results57%
7GPT-3.5 Turbopublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results55%
8Llama-2-7b-chat-hfpublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results55%
9Qwen 2 (72B)published-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results55%
10gemini-1.0-propublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results54%
11Qwen2.5 7B Instructpublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results53.9%
12DeepSeek R1 Distill Qwen 1.5Bpublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results53.6%
13DeepSeek V3published-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results53.6%
14Llama 3.2 3Bpublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results52.4%
15Qwen2 7B Instructpublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results52%
16Mistral (7B) Instruct v0.3published-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results49.5%
17Llama 2 70bpublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results49%
18Llama 3.1 70Bpublished-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results44%
19Mixtral 8X7b V0.1published-demo-leaderboard, CIKM18, Acc· TheFinAI public numeric results42%

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.