Skip to content

Benchmark

FinBen FOMC Acc

Scores are percentages. Higher is better.

Models measured
16
Scores recorded
16
Sources
1
IQ weight
1.12

Score distribution

51.2%
Mean
55.7%
Median
13.2%
Std dev
34.9%
10th percentile
64%
90th percentile
21%
Min
21%69%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.12 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
1GPT-4 Turbopublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results69%
2Qwen2 7B Instructpublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results64%
3Qwen2.5 7B Instructpublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results62.5%
4codellama-7bpublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results62.3%
5Qwen2.5 7Bpublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results60.7%
6gemini-1.0-propublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results60%
7GPT-3.5 Turbopublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results60%
8DeepSeek V3published-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results55.7%
9Mistral (7B) Instruct v0.3published-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results53.6%
10Llama 3.2 3Bpublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results51%
11Llama-2-7b-chat-hfpublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results49%
12Llama 2 70bpublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results47%
13Mixtral 8X7b V0.1published-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results35%
14DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results34.9%
15code-llama-7b-instructpublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results32.9%
16DeepSeek R1 Distill Qwen 1.5Bpublished-demo-leaderboard, FOMC, Acc· TheFinAI public numeric results21%

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.