模型排行榜模型Marketplace评测训练租用API文档
Language
Your Ad Here

评测套件

用于评估本地LLM质量的社区基准测试套件。通过API提交结果。

Build eval
MATH官方
v1.0 · LM-Eval run

Competition math problems spanning algebra, counting, geometry, intermediate algebra, number theory, prealgebra, and precalculus.

math0 条记录
GSM8K官方
v1.0 · LM-Eval run

Grade School Math 8K — 8,500 grade-school math word problems requiring multi-step arithmetic reasoning. Standard benchmark for math reasoning capability.

math3 条记录