DAYJOB: A Benchmark for Long-Horizon Professional Work

arXiv:2610.01306 · cs.AI, cs.CL · Submitted 2026-10-01 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-10-01

Updated: 2026-10-01

Code: https://github.com/surge-ai/dayjob

Terminology

• Benchmark — 26× in this paper · explained in 2 episodes
• Benchmarking — 5× in this paper · explained in 3 episodes
• In International Conference on Learning Representations — 4× in this paper
• APEX — 3× in this paper · explained in 1 episode
• In International Conference on Machine Learning — 3× in this paper
• Consistency — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• HealthBench: Evaluating Large Language Models Towards Improved Human Health
• Finance Agent Benchmark: Benchmarking LLMs on Real-world Financial Research Tasks
• GDP.pdf: Benchmarking Grounded Multimodal Reasoning over Professional PDF Documents
• Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
• CRMArena-Pro: Holistic Assessment of LLM Agents Across Diverse Business Scenarios and Interactions
• FinanceBench: A New Benchmark for Financial Question Answering
• Remote Labor Index: Measuring AI Automation of Remote Work
• ComplexConstraints and Beyond: Expert Rubrics for RLVR
• EnterpriseBench Corecraft: Training Generalizable Agents on High-Fidelity RL Environments
• HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following
• GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks
• AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments
• The AI Productivity Index (APEX)
• The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection