Skip to content

Benchmark

FinBen FinArg-ACC MicroF1

Scores are percentages. Higher is better.

Models measured
19
Scores recorded
19
Sources
1
IQ weight
0.94

Score distribution

46.6%
Mean
44.8%
Median
10.9%
Std dev
33.5%
10th percentile
60%
90th percentile
24.6%
Min
24.6%65.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.94 for chat models, measured over 19 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1DeepSeek V3published-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results65.7%
2Llama 3.1 70Bpublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results65%
3GPT-4 Turbopublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results60%
4Llama 2 70bpublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results58%
5Qwen 2 (72B)published-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results57%
6Llama 3.1 8Bpublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results53%
7GPT-3.5 Turbopublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results50%
8DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results47.7%
9Llama-2-7b-chat-hfpublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results46%
10Qwen2.5 7B Instructpublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results44.8%
11codellama-7bpublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results44%
12Qwen2 7B Instructpublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results43%
13Llama 3.2 3Bpublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results42.8%
14DeepSeek R1 Distill Qwen 1.5Bpublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results42.5%
15Mixtral 8X7b V0.1published-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results39%
16Mistral (7B) Instruct v0.3published-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results37.1%
17Qwen2.5 7Bpublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results33.5%
18gemini-1.0-propublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results31%
19code-llama-7b-instructpublished-demo-leaderboard, FinArg-ACC, MicroF1· TheFinAI public numeric results24.6%

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.