Skip to content

Benchmark

FinBen portoseguro F1

Scores are percentages. Higher is better.

Models measured
16
Scores recorded
16
Sources
1
IQ weight
0.51

Score distribution

43.3%
Mean
54.5%
Median
38.5%
Std dev
0.18%
10th percentile
95.2%
90th percentile
0%
Min
0%95.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.51 for chat models, measured over 16 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen2.5 7Bpublished-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results95.5%
2codellama-7bpublished-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results95.2%
3gemini-1.0-propublished-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results95%
4Qwen2.5 7B Instructpublished-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results90%
5DeepSeek V3published-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results79.7%
6Mixtral 8X7b V0.1published-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results72%
7GPT-4 Turbopublished-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results55%
8Llama 3.2 3Bpublished-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results54.5%
9GPT-3.5 Turbopublished-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results20%
10Llama 2 70bpublished-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results17%
11DeepSeek R1 Distill Qwen 1.5Bpublished-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results11.6%
12Mistral (7B) Instruct v0.3published-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results5.5%
13Llama-2-7b-chat-hfpublished-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results1%
14code-llama-7b-instructpublished-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results0.18%
15DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, portoseguro, F1· TheFinAI public numeric results0.18%
16Qwen2 7B Instructpublished-demo-leaderboard, portoseguro, F1· 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.