List your company

Narrative Understanding on SC

98.7First-Token AccuracyPhi-4-14B
68.43676.29384.1592.007May 21, 2025

Evaluation results

MethodLinks
Phi-4-14BStrategy=Prompt Engineering2025.0598.7
Phi-4-14BStrategy=Prefilling2025.0598.7
Ministral-8BStrategy=Prefilling2025.0598.2
Phi-4-14BStrategy=FTP2025.0598.2
Gemma-2-9BStrategy=Prompt Engineering2025.0597.9
Gemma-2-9BStrategy=Prefilling2025.0597.9
Qwen-2-7BStrategy=Prompt Engineering2025.0597.7
Gemma-2-9BStrategy=FTP2025.0597.6
Ministral-8BStrategy=FTP2025.0597.4
Qwen-2-7BStrategy=Prefilling2025.0597.3
Mistral-Nemo-12BStrategy=FTP2025.0597.3
Qwen-2-7BStrategy=FTP2025.0597.1
Mistral-Nemo-12BStrategy=Prefilling2025.0596.9
Llama-3.1-8BStrategy=Prefilling2025.0596.4
Zephyr-7BStrategy=FTP2025.0596
Zephyr-7BStrategy=Prefilling2025.0596
Llama-3.1-8BStrategy=Prompt Engineering2025.0594.8
Ministral-8BStrategy=Prompt Engineering2025.0594
Llama-3.1-8BStrategy=FTP2025.0593.2
Gemma-7BStrategy=Prefilling2025.0592
Zephyr-7BStrategy=Prompt Engineering2025.0591.7
Mistral-Nemo-12BStrategy=Prompt Engineering2025.0589.9
Gemma-7BStrategy=Prompt Engineering2025.0577.2
Gemma-7BStrategy=FTP2025.0569.6