List your company

Narrative Understanding on MC-T

93.3First-Token AccuracyZephyr-7B
58.77267.73676.785.664May 21, 2025

Evaluation results

MethodLinks
Zephyr-7BStrategy=Prefilling2025.0593.3
Mistral-Nemo-12BStrategy=Prefilling2025.0593.3
Mistral-Nemo-12BStrategy=Prompt Engineering2025.0592.8
Mistral-Nemo-12BStrategy=FTP2025.0592.4
Ministral-8BStrategy=Prefilling2025.0591.9
Ministral-8BStrategy=FTP2025.0591.5
Gemma-7BStrategy=Prompt Engineering2025.0591
Gemma-7BStrategy=Prefilling2025.0591
Ministral-8BStrategy=Prompt Engineering2025.0590
Llama-3.1-8BStrategy=Prompt Engineering2025.0589.7
Qwen-2-7BStrategy=FTP2025.0588.3
Qwen-2-7BStrategy=Prefilling2025.0586.1
Phi-4-14BStrategy=Prefilling2025.0586.1
Zephyr-7BStrategy=Prompt Engineering2025.0585.2
Qwen-2-7BStrategy=Prompt Engineering2025.0585.1
Llama-3.1-8BStrategy=Prefilling2025.0582.5
Phi-4-14BStrategy=FTP2025.0582.5
Llama-3.1-8BStrategy=FTP2025.0582.1
Phi-4-14BStrategy=Prompt Engineering2025.0582
Gemma-2-9BStrategy=Prefilling2025.0578.5
Gemma-2-9BStrategy=Prompt Engineering2025.0577.1
Gemma-2-9BStrategy=FTP2025.0572.2
Zephyr-7BStrategy=FTP2025.0569.1
Gemma-7BStrategy=FTP2025.0560.1