Skip to content

Benchmark

FinBen CD F1

Scores are percentages. Higher is better.

Models measured
19
Scores recorded
19
Sources
1
IQ weight
1.91

Score distribution

0.412%
Mean
0.02%
Median
0.727%
Std dev
0%
10th percentile
1%
90th percentile
0%
Min
0%3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.91 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
1gemini-1.0-propublished-demo-leaderboard, CD, F1· TheFinAI public numeric results3%
2GPT-4 Turbopublished-demo-leaderboard, CD, F1· TheFinAI public numeric results1%
3Llama 2 70bpublished-demo-leaderboard, CD, F1· TheFinAI public numeric results1%
4Qwen 2 (72B)published-demo-leaderboard, CD, F1· TheFinAI public numeric results1%
5Qwen2.5 7B Instructpublished-demo-leaderboard, CD, F1· TheFinAI public numeric results0.9%
6Qwen2.5 7Bpublished-demo-leaderboard, CD, F1· TheFinAI public numeric results0.66%
7codellama-7bpublished-demo-leaderboard, CD, F1· TheFinAI public numeric results0.12%
8DeepSeek V3published-demo-leaderboard, CD, F1· TheFinAI public numeric results0.11%
9code-llama-7b-instructpublished-demo-leaderboard, CD, F1· TheFinAI public numeric results0.02%
10DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, CD, F1· TheFinAI public numeric results0.02%
11DeepSeek R1 Distill Qwen 1.5Bpublished-demo-leaderboard, CD, F1· TheFinAI public numeric results0%
12GPT-3.5 Turbopublished-demo-leaderboard, CD, F1· TheFinAI public numeric results0%
13Llama 3.1 70Bpublished-demo-leaderboard, CD, F1· TheFinAI public numeric results0%
14Llama 3.1 8Bpublished-demo-leaderboard, CD, F1· TheFinAI public numeric results0%
15Llama 3.2 3Bpublished-demo-leaderboard, CD, F1· TheFinAI public numeric results0%
16Llama-2-7b-chat-hfpublished-demo-leaderboard, CD, F1· TheFinAI public numeric results0%
17Mistral (7B) Instruct v0.3published-demo-leaderboard, CD, F1· TheFinAI public numeric results0%
18Mixtral 8X7b V0.1published-demo-leaderboard, CD, F1· TheFinAI public numeric results0%
19Qwen2 7B Instructpublished-demo-leaderboard, CD, F1· TheFinAI public numeric results0%

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.