摘要:Hugging Face 上的基准数据集现在可以托管排行榜。模型自行存储其评估分数。所有内容相互关联。社区可以通过 PR 提交结果。经过验证的徽章可证明结果可复现。
评估机制已失效
让我们正视 2026 年评估领域的现状。MMLU 在 91% 以上已趋饱和。GSM8K 达到 94% 以上。HumanEval 已被攻克。然而,根据使用报告,一些在基准测试中表现出色的模型,仍然无法可靠地浏览网页、编写生产级代码,或在处理多步骤任务时避免模型幻觉。基准测试分数与实际性能之间存在明显差距。
此外,已报告的基准测试分数内部也存在差距。多个来源报告了不同的结果。从模型卡到论文,再到评估平台,报告分数之间缺乏一致性。其结果是,社区缺乏一个单一的真实信息来源。
我们正在推出的功能
去中心化且透明的评估报告。
我们将把 Hugging Face Hub 上的评估工作引向一个新方向,即通过去中心化报告,允许整个社区公开提交基准测试的分数。首先,我们将从 4 个基准测试的候选名单开始,并随着时间的推移扩展到最相关的基准测试。
对于基准测试:数据集仓库现在可以注册为基准测试(MMLU-Pro、GPQA、HLE 已上线)。它们会自动聚合来自 Hub 各处报告的结果,并在数据集卡中显示排行榜。基准测试通过 eval.yaml 文件(基于 Inspect AI 格式)定义评估规范,以便任何人都可以复现。报告的结果需要与任务定义保持一致。
对于模型:评估分数存放在模型仓库的 `.eval_results/*.yaml` 文件中。它们会显示在模型卡上,并反馈到基准测试数据集中。模型作者提交的结果以及针对结果发起的开放拉取请求都会被汇总。模型作者将能够关闭分数相关的 PR 并隐藏结果。
面向社区:任何用户都可以通过 PR 提交任意模型的评估结果。结果会显示为“社区”来源,无需等待模型作者合并或关闭。社区可以链接到论文、模型卡、第三方评估平台等来源,或查看评估日志。社区可以像对待任何 PR 一样讨论评分。由于 Hub 基于 Git,因此会保留评估添加时间、修改时间等历史记录。来源示例如下。
要了解更多关于评估结果的信息,请查阅文档。
Hub 中的模型评分
为何重要
去中心化评估将公开社区中已存在于模型卡和论文等来源中的评分。通过公开这些评分,社区可以在此基础上进行聚合、跟踪和理解整个领域的评分。此外,所有评分都将通过 Hub API 公开,从而便于聚合和构建精选排行榜、仪表盘等。
社区评估不会取代基准测试,因此排行榜和已发布结果的封闭评估仍然至关重要。然而,我们认为,基于可复现的评估规范提供开放的评估结果,对于推动该领域发展具有重要意义。
这不会解决基准测试饱和问题,也不会缩小基准测试与现实之间的差距。它也不会阻止在测试集上进行训练。但它通过公开评估内容、评估方式、评估时间和评估人员,让整个游戏变得透明可见。
最重要的是,我们希望将 Hub 打造成一个构建和共享可复现基准测试的活跃场所,尤其关注那些更能挑战 SOTA 模型的新任务和新领域。
阅读文档:要了解更多关于评估结果的信息,请查阅文档。
添加评估结果:将您进行的评估以 YAML 文件形式发布到任意模型仓库的 `.eval_results/` 目录下。
查看基准测试数据集上的评分。
注册新基准测试:将 `eval.yaml` 添加到您的数据集仓库,并联系我们以列入候选名单。
该功能目前处于测试阶段。我们正在进行开放式构建。欢迎提供反馈。
TL;DR: Benchmark datasets on Hugging Face can now host leaderboards. Models store their own eval scores. Everything links together. The community can submit results via PR. Verified badges prove that the results can be reproduced.
Evaluation is broken
Let's be real about where we are with evals in 2026. MMLU is saturated above 91%. GSM8K hit 94%+. HumanEval is conquered. Yet some models that ace benchmarks still can't reliably browse the web, write production code, or handle multi-step tasks without hallucinating, based on usage reports. There is a clear gap between benchmark scores and real-world performance.
Furthermore, there is another gap within reported benchmark scores. Multiple sources report different results. From Model Cards, to papers, to evaluation platforms, there is no alignment in reported scores. The result is that the community lacks a single source of truth.
What We're Shipping
Decentralized and transparent evaluation reporting.
We are going to take evaluations on the Hugging Face Hub in a new direction by decentralizing reporting and allowing the entire community to openly report scores for benchmarks. At first, we will start with a shortlist of 4 benchmarks and over time we’ll expand to the most relevant benchmarks.
For Benchmarks: Dataset repos can now register as benchmarks (MMLU-Pro, GPQA, HLE are already live). They automatically aggregate reported results from across the Hub and display leaderboards in the dataset card. The benchmark defines the eval spec via eval.yaml, based on the Inspect AI format, so anyone can reproduce it. The reported results need to align with the task definition.
For Models: Eval scores live in .eval_results/*.yaml in the model repo. They appear on the model card and are fed into benchmark datasets. Both the model author’s results and open pull requests for results will be aggregated. Model authors will be able to close score PR and hide results.
For the Community: Any user can submit evaluation results for any model via a PR. Results get shown as "community", without waiting for model authors to merge or close. The community can link to sources like a paper, Model Card, third-party evaluation platform, or inspect eval logs. The community can discuss scores like any PR. Since the Hub is Git based, there is a history of when evals were added, when changes were made, etc. The sources look like below.
To learn more about evaluation results, check out the docs.
Model scores in the Hub
Why This Matters
Decentralizing evaluation will expose scores that already exist across the community in sources like model cards and papers. By exposing these scores, the community can build on top of them to aggregate, track, and understand scores across the field. Also, all scores will be exposed via Hub APIs, making it easy to aggregate and build curated leaderboards, dashboards, etc.
Community evals do not replace benchmarks so leaderboards and closed evals with published results are still crucial. However, we believe it's important to contribute to the field with open eval results based on reproducible eval specs.
This won't solve benchmark saturation or close the benchmark-reality gap. Nor will it stop training on test sets. But it makes the game visible by exposing what is evaluated, how, when, and by whom.
Mostly, we hope to make the Hub an active place to build and share reproducible benchmarks. Particularly focusing on new tasks and domains that challenge SOTA models more.
Read the docs: To learn more about evaluation results, check out the docs.
Add eval results: Publish the evals you conducted as YAML files in .eval_results/ on any model repo.
Check out the scores on the benchmark dataset.
Register a new benchmark: Add eval.yaml to your dataset repo and contact us to be included in the shortlist.
The feature is in beta. We're building in the open. Feedback welcome.