Skip to Main Content

[標題]最新消息

Test Results of the November 2025 Open Source 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 green; figures below 50% are marked in pink.

✪This test cycle includes 18 newly added models (3 small models and 15 large models).

  • Language Model Benchmark / Small Models (13B and below)

Language Model Benchmark / Small Models (13B and below), please refer to the “Small” worksheet in the files below, “Test Results of the November 2025 OpenSource Models(Small Models).ods” or “Test Results of the November 2025 OpenSource Models(Small Models).xlsx

  • Language Model Benchmark / Large Models (above 13B)

Language Model Benchmark / Large Models (above 13B), please refer to the “Large” worksheet in the files below, “Test Results of the November 2025 OpenSource Models(Large Models).ods” or “Test Results of the November 2025 OpenSource Models(Large Models).xlsx 
 

Downloads:
Test Results of the November 2025 OpenSource Models(Large and Small Models).ods
Test Results of the November 2025 OpenSource Models(Large and Small Models).xlsx