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
全部官方LM-Eval runsCustom server-sidecodingknowledgemathreasoningtruthfulnesswriting
MMLU 5-shot
v1.0 · LM-Eval run

Massive Multitask Language Understanding via EleutherAI lm-evaluation-harness task mmlu, 5-shot, exact-match/accuracy style scoring.

knowledge0 条记录
Probe
v1.0 · LM-Eval run
knowledge1 条记录