Independent MMLU-Pro evaluation

#4
by yaronr - opened

Hi Qwen team,

I'm pleased to share our independent evaluation of the model using our implementation of the MMLU-Pro benchmark.
The results demonstrate impressive performance for the model across multiple categories compared with other models.
I hope you find this useful.

Hii kaise ho

@Deathgod7890 Main thik hoon, shukriya

Tum kya kar rahi ho

You may find additional analysis for detailed categories, under a new tab, 'Unity Subjects'

Sign up or log in to comment