Share your thoughts, 1 month free Claude Pro on usSee more

Narrative Understanding on SC

98.7First-Token Accuracy

Phi-4-14B

Updated 12d ago

Evaluation Results

Method	Links
Phi-4-14B 2025.05		98.7
Phi-4-14B 2025.05		98.7
Ministral-8B 2025.05		98.2
Phi-4-14B 2025.05		98.2
Gemma-2-9B 2025.05		97.9
Gemma-2-9B 2025.05		97.9
Qwen-2-7B 2025.05		97.7
Gemma-2-9B 2025.05		97.6
Ministral-8B 2025.05		97.4
Qwen-2-7B 2025.05		97.3
Mistral-Nemo-12B 2025.05		97.3
Qwen-2-7B 2025.05		97.1
Mistral-Nemo-12B 2025.05		96.9
Llama-3.1-8B 2025.05		96.4
Zephyr-7B 2025.05		96
Zephyr-7B 2025.05		96
Llama-3.1-8B 2025.05		94.8
Ministral-8B 2025.05		94
Llama-3.1-8B 2025.05		93.2
Gemma-7B 2025.05		92
Zephyr-7B 2025.05		91.7
Mistral-Nemo-12B 2025.05		89.9
Gemma-7B 2025.05		77.2
Gemma-7B 2025.05		69.6