Skip to content

Benchmark

FinBen TSA-Spanish Macro F1

Scores are percentages. Higher is better.

Models measured
6
Scores recorded
6
Sources
1
IQ weight
1.26

Score distribution

19.9%
Mean
11.7%
Median
17.6%
Std dev
6.1%
10th percentile
44.6%
90th percentile
5.9%
Min
5.9%44.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.26 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Mistral (7B) Instruct v0.3published-demo-leaderboard, TSA-Spanish, Macro F1· TheFinAI public numeric results44.6%
2Qwen2.5 7Bpublished-demo-leaderboard, TSA-Spanish, Macro F1· TheFinAI public numeric results44.6%
3Qwen2.5 7B Instructpublished-demo-leaderboard, TSA-Spanish, Macro F1· TheFinAI public numeric results11.7%
4code-llama-7b-instructpublished-demo-leaderboard, TSA-Spanish, Macro F1· TheFinAI public numeric results6.2%
5codellama-7bpublished-demo-leaderboard, TSA-Spanish, Macro F1· TheFinAI public numeric results6.1%
6Llama 3.2 3Bpublished-demo-leaderboard, TSA-Spanish, Macro F1· TheFinAI public numeric results5.9%

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.