Skip to content

Benchmark

FinBen Australian MCC

Higher scores are better.

Models measured
14
Scores recorded
14
Sources
1
IQ weight
2.29

Score distribution

0.047
Mean
0
Median
0.15
Std dev
-0.096
10th percentile
0.255
90th percentile
-0.139
Min
-0.1390.47
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.29 for chat models, measured over 14 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 Turbopublished-demo-leaderboard, Australian, MCC· TheFinAI public numeric results0.47
2DeepSeek V3published-demo-leaderboard, Australian, MCC· TheFinAI public numeric results0.255
3Qwen2.5 7B Instructpublished-demo-leaderboard, Australian, MCC· TheFinAI public numeric results0.132
4Qwen2 7B Instructpublished-demo-leaderboard, Australian, MCC· TheFinAI public numeric results0.1
5gemini-1.0-propublished-demo-leaderboard, Australian, MCC· TheFinAI public numeric results0
6GPT-3.5 Turbopublished-demo-leaderboard, Australian, MCC· TheFinAI public numeric results0
7Llama 2 70bpublished-demo-leaderboard, Australian, MCC· TheFinAI public numeric results0
8Llama 3.2 3Bpublished-demo-leaderboard, Australian, MCC· TheFinAI public numeric results0
9Llama-2-7b-chat-hfpublished-demo-leaderboard, Australian, MCC· TheFinAI public numeric results0
10Mixtral 8X7b V0.1published-demo-leaderboard, Australian, MCC· TheFinAI public numeric results0
11Qwen2.5 7Bpublished-demo-leaderboard, Australian, MCC· TheFinAI public numeric results0
12Mistral (7B) Instruct v0.3published-demo-leaderboard, Australian, MCC· TheFinAI public numeric results-0.0598
13codellama-7bpublished-demo-leaderboard, Australian, MCC· TheFinAI public numeric results-0.0965
14DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, Australian, MCC· TheFinAI public numeric results-0.139

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.