Skip to content

Benchmark

FinBen travelinsurance F1

Scores are percentages. Higher is better.

Models measured
16
Scores recorded
16
Sources
1
IQ weight
0.42

Score distribution

39.2%
Mean
20%
Median
39.6%
Std dev
0%
10th percentile
97.8%
90th percentile
0%
Min
0%98%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.42 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 7B Instructpublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results98%
2Qwen2.5 7Bpublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results97.8%
3Qwen2.5 7B Instructpublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results97.8%
4codellama-7bpublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results89.3%
5DeepSeek R1 Distill Qwen 1.5Bpublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results74.4%
6DeepSeek R1 Distill Qwen 7Bpublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results59.8%
7GPT-4 Turbopublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results55%
8GPT-3.5 Turbopublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results20%
9Llama 2 70bpublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results17%
10DeepSeek V3published-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results11.5%
11Mistral (7B) Instruct v0.3published-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results5.9%
12code-llama-7b-instructpublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results0.04%
13Llama 3.2 3Bpublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results0.04%
14gemini-1.0-propublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results0%
15Llama-2-7b-chat-hfpublished-demo-leaderboard, travelinsurance, F1· TheFinAI public numeric results0%
16Mixtral 8X7b V0.1published-demo-leaderboard, travelinsurance, 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.