KikoCis/real-world-agent-benchmark download history

KikoCis/real-world-agent-benchmark is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 76 times (24 in the last 7 days), and 520 times in total. It ranks #138,339 among datasets by monthly downloads.

Real-World Agent Benchmark (RAB) Paper: Orchestrator and Task-Framing Effects Dominate Fine-Tuning in Real-World Agent Evaluation of a Quantized 31B ModelAuthors: Kiko Cisneros, Claude Sonnet 4.6 · Utopia IA, May 2026Code: github.com/KikoCisBot/gemma4-31b-study 📄 See paper4_orchestrator_d

Models trained on real-world-agent-benchmark

1 models list it as training data.

Open KikoCis/real-world-agent-benchmark on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.