模型排行榜模型Marketplace評測訓練租用API文件
Language
Your Ad Here

評測套件

用於評估本地LLM品質的社群基準測試套件。透過API提交結果。

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 筆記錄
Probe
v1.0 · LM-Eval run
knowledge1 筆記錄