论文34
LlamaIndex 在 ParseBench-2 上评测 20+ 开源权重模型
原标题:We’ve benchmarked over 20+ open-weight models on ParseBench-2 🔥
LlamaIndex 在 ParseBench-2 上评测了 20+ 个开源权重模型,榜单已在 Hugging Face 公开。评测细化了表格、图表、格式等维度,展示开源权重模型在哪些具体场景表现更优,完整拆解见 parsebench.ai。团队正快速扩充评测模型并迭代基准本身,过去几天月下载量已达约 30k+。
中文译文尚未完成,先为你展示原文。
We’ve benchmarked over 20+ open-weight models on ParseBench-2 🔥
The leaderboard is fully public and on @huggingface.
Perhaps even more importantly, it’s important to know the specifics of where open-weight models do better than others: across tables, charts, formatting, and more. The full breakdown is shown on ParseBench-2: https://www.parsebench.ai/
We’re rapidly benchmarking more models and shipping iterations on the benchmark itself. We’ve hit ~30k+ monthly downloads in the past few days.
Hugging Face: https://huggingface.co/datasets/llamaindex/ParseBench-2
Leaderboard: https://www.parsebench.ai/
