Skip to Main Content

[標題]最新消息

Test Results of the February 2026 OpenSource Models

Sorted by the region of the developing organization: light orange represents European models, light blue represents U.S. models, light green represents local models, and light purple represents Chinese models.

Explanation of percentage values: figures above 50% are marked in black; figures below 50% are marked in red.

✪This test cycle includes newly added 6 small models.

  • Language Model Benchmark / Small Models (Below 13B Parameters)

Language Model Benchmark / Small Models (13B and below)Please refer to the relevant files below,Test Results of the February 2026  OpenSource Models(Small Models).ods

  • Language Model Benchmark / Large Models (Above 13B Parameters)

Language Model Benchmark / Large Models (above 13B) Please refer to the relevant files below,Test Results of the February 2026 OpenSource Models(Large Models).ods 
 

Downloads:
Test Results of the February 2026 OpenSource Models(Small Models).ods
Test Results of the February 2026 OpenSource Models(Large Models).ods