From 18fcf3ef14deb63afe56d9443e26d62427b47338 Mon Sep 17 00:00:00 2001 From: genitrix Date: Sat, 15 Aug 2026 16:07:33 +0800 Subject: [PATCH] Add Dr. Bench --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 2e85ebc..7122ec5 100644 --- a/README.md +++ b/README.md @@ -203,6 +203,7 @@ Multi-agent evaluation is an emerging area that tests how agents collaborate, co These benchmarks aim to measure agent capabilities on tasks that resemble actual human work — information gathering, analysis, multi-step problem solving, and professional expertise. +- [**Dr. Bench**](https://github.com/EVIGBYEN/DrBench) — Evaluates deep-research agents on 214 expert-curated, long-form report tasks with reference bundles and metrics for semantic quality, topical focus, and retrieval trustworthiness. - [**GAIA**](https://huggingface.co/gaia-benchmark) — Benchmark for general AI assistants that require multi-step reasoning, tool use, and real-world problem solving. Tasks are designed so that a human can verify the answer easily but solving requires genuine capability. Meta / HuggingFace. - [**GDPval**](https://arxiv.org/abs/2510.04374) — Benchmark for economically valuable expert work across occupations and sectors. Maps agent capabilities to real economic value. - [**GDPval in Inspect Evals**](https://github.com/UKGovernmentBEIS/inspect_evals) — Example of integrating GDPval into the UK AI Safety Institute's broader open evaluation ecosystem.