Skip to content

Benchmark

FinBen TSA RMSE

Lower scores are better.

Models measured
18
Scores recorded
18
Sources
1
IQ weight
0.00

Score distribution

0.421
Mean
0.42
Median
0.145
Std dev
0.278
10th percentile
0.578
90th percentile
0.165
Min
0.1650.71
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 18 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Llama 3.2 3Bpublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.165
2Llama 3.1 8Bpublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.17
3Mistral (7B) Instruct v0.3published-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.278
4Qwen 2 (72B)published-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.3
5Qwen2.5 7B Instructpublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.304
6Qwen2.5 7Bpublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.368
7gemini-1.0-propublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.37
8codellama-7bpublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.374
9code-llama-7b-instructpublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.387
10Llama 3.1 70Bpublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.42
11Qwen2 7B Instructpublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.43
12GPT-4 Turbopublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.5
13Mixtral 8X7b V0.1published-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.5
14GPT-3.5 Turbopublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.53
15Llama 2 70bpublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.57
16DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.578
17DeepSeek V3published-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.619
18Llama-2-7b-chat-hfpublished-demo-leaderboard, TSA, RMSE· TheFinAI public numeric results0.71

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.