deepseek-harness

ai-tools / GitHub

SCORE

deepseek-harness is an evaluation framework developed by DeepSeek AI for benchmarking large language models. It provides standardized testing infrastructure to assess model performance across a range of tasks and datasets. The repository is hosted on GitHub and has accumulated over 17,000 stars.

VISIT PRODUCT →

Sources (1)

GitHub

https://github.com/deepseek-ai/deepseek-harness

17,652 STARS

Score Breakdown

Traction

raw 18827.00 · weight 35%

35.0pts

Novelty

0 days old · weight 20%

20.0pts

Source diversity

1 source · weight 10%

3.3pts

AI quality

raw 72.00 · weight 35%

25.2pts

Solid LLM evaluation framework with strong community traction (17K stars), but appears to be a fork/adaptation of existing harness tools with limited differentiation.

Final Score84/100