Skip to content

Benchmark

FinBen FINER-ORD F1

Scores are percentages. Higher is better.

Models measured
7
Scores recorded
7
Sources
1
IQ weight
0.98

Score distribution

6%
Mean
2.8%
Median
5.9%
Std dev
0.61%
10th percentile
13.1%
90th percentile
0.41%
Min
0.41%15%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.98 for chat models, measured over 7 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen2 7B Instructpublished-demo-leaderboard, FINER-ORD, F1· TheFinAI public numeric results15%
2Qwen2.5 7B Instructpublished-demo-leaderboard, FINER-ORD, F1· TheFinAI public numeric results13.1%
3codellama-7bpublished-demo-leaderboard, FINER-ORD, F1· TheFinAI public numeric results9.7%
4Qwen2.5 7Bpublished-demo-leaderboard, FINER-ORD, F1· TheFinAI public numeric results2.8%
5Llama 3.2 3Bpublished-demo-leaderboard, FINER-ORD, F1· TheFinAI public numeric results0.77%
6Mistral (7B) Instruct v0.3published-demo-leaderboard, FINER-ORD, F1· TheFinAI public numeric results0.61%
7DeepSeek R1 Distill Qwen 1.5Bpublished-demo-leaderboard, FINER-ORD, F1· TheFinAI public numeric results0.41%

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.