Skip to content

Benchmark

FinBen TATQA EmAcc

Scores are percentages. Higher is better.

Models measured
19
Scores recorded
19
Sources
1
IQ weight
0.33

Score distribution

5.2%
Mean
0.36%
Median
10.5%
Std dev
0%
10th percentile
13%
90th percentile
0%
Min
0%44%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.33 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
1Llama 3.1 70Bpublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results44%
2gemini-1.0-propublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results18%
3GPT-4 Turbopublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results13%
4Qwen2.5 7Bpublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results12.6%
5Llama 3.1 8Bpublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results4%
6Llama-2-7b-chat-hfpublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results3%
7Mistral (7B) Instruct v0.3published-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results1.7%
8Llama 2 70bpublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results1%
9Mixtral 8X7b V0.1published-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results1%
10Llama 3.2 3Bpublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results0.36%
11code-llama-7b-instructpublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results0.06%
12codellama-7bpublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results0.06%
13DeepSeek R1 Distill Qwen 1.5Bpublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results0%
14DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results0%
15DeepSeek V3published-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results0%
16GPT-3.5 Turbopublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results0%
17Qwen 2 (72B)published-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results0%
18Qwen2 7B Instructpublished-demo-leaderboard, TATQA, EmAcc· TheFinAI public numeric results0%
19Qwen2.5 7B Instructpublished-demo-leaderboard, TATQA, EmAcc· 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.