Skip to content

Benchmark

Open Greek FinLLM QA raw score

Higher scores are better.

Models measured
20
Scores recorded
20
Sources
1
IQ weight
0.91

Score distribution

0.429
Mean
0.396
Median
0.222
Std dev
0.218
10th percentile
0.738
90th percentile
0
Min
00.813
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.91 for chat models, measured over 20 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT-4.5 Previewgreek-contents, QA, QA Raw· TheFinAI public numeric results0.813
2GPT 4ogreek-contents, QA, QA Raw· TheFinAI public numeric results0.782
3Qwen2.5 72B Instructgreek-contents, QA, QA Raw· TheFinAI public numeric results0.738
4GPT 4greek-contents, QA, QA Raw· TheFinAI public numeric results0.707
5DeepSeek Chatgreek-contents, QA, QA Raw· TheFinAI public numeric results0.622
6Qwen2.5 32B Instructgreek-contents, QA, QA Raw· TheFinAI public numeric results0.604
7Llama 3 70B Instructgreek-contents, QA, QA Raw· TheFinAI public numeric results0.596
8Mistral (7B) Instruct v0.3greek-contents, QA, QA Raw· TheFinAI public numeric results0.431
9Qwen2.5 7B Instructgreek-contents, QA, QA Raw· TheFinAI public numeric results0.427
10Llama 3.1 8B Instructgreek-contents, QA, QA Raw· TheFinAI public numeric results0.396
11Qwen2.5 1.5B Instructgreek-contents, QA, QA Raw· TheFinAI public numeric results0.356
12Llama 3 8B Instructgreek-contents, QA, QA Raw· TheFinAI public numeric results0.333
13Gemma 2 9B ITgreek-contents, QA, QA Raw· TheFinAI public numeric results0.307
14Mistral (7B) Instruct v0.1greek-contents, QA, QA Raw· TheFinAI public numeric results0.298
15QwQ 32Bgreek-contents, QA, QA Raw· TheFinAI public numeric results0.298
16Llama 3.2 1B Instructgreek-contents, QA, QA Raw· TheFinAI public numeric results0.293
17Gemma 2 27B ITgreek-contents, QA, QA Raw· TheFinAI public numeric results0.253
18Gemma 2 2B ITgreek-contents, QA, QA Raw· TheFinAI public numeric results0.218
19GPT-4o minigreek-contents, QA, QA Raw· TheFinAI public numeric results0.116
20GPT-3.5 Turbogreek-contents, QA, QA Raw· 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.