# DAYJOB Healthcare > The healthcare track of Surge AI's DAYJOB: 50 long clinical, pharmacy, payer and quality-assurance assignments that an agent must complete to an expert checklist. Canonical page: https://benchlm.ai/benchmarks/dayjob-healthcare - Category: [Agentic](/agentic) - Last updated: Latest evaluation November 3, 2026 Evaluation results published by [Surge AI](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare). undefined Each task places an agent in a realistic healthcare workspace with records such as longitudinal patient charts, imaging and lab reports, payer contracts, claims queues, dispensing logs or batch records. The agent must produce work such as a physician handoff, a clinical appeal or a regulatory workpaper. Each task is a short workplace request backed by a multi-file workspace. An agent (OpenHands SDK harness on Kaggle) must produce finished deliverables, which a judge model grades against an expert-written checklist of binary criteria. A trial passes only when every criterion passes, and each model gets five attempts per task; the score is the share of passing trials. The track has 50 tasks across five subfields and 2,785 rubric criteria, with a median of 49 per task. Scores are low by design: models satisfy most individual criteria but rarely all of them. Results depend on the Kaggle agent harness and the judge model, and Surge AI keeps a separate leaderboard of its own. Kaggle reports close agreement between the two, not identity. The tasks are simulated workspaces, not live patient care, and the score does not establish clinical safety. These are published source configurations. Compare the disclosed settings before treating a score difference as a model difference. - [Kaggle leaderboard and Apache 2.0 declaration](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) - [Surge AI DAYJOB announcement](https://surgehq.ai/blog/dayjob) - [Published leaderboard data](https://www.kaggle.com/api/v1/benchmarks/surge-ai/dayjob-healthcare/leaderboard) ## About DAYJOB Healthcare - Year: 2026 - Tasks: 50 long-horizon healthcare tasks across five subfields - Format: Agent deliverables graded all-or-nothing against expert rubrics - Difficulty: Long-horizon clinical and healthcare operations work Each task places an agent in a realistic healthcare workspace with records such as longitudinal patient charts, imaging and lab reports, payer contracts, claims queues, dispensing logs or batch records. The agent must produce work such as a physician handoff, a clinical appeal or a regulatory workpaper. Each task is a short workplace request backed by a multi-file workspace. An agent (OpenHands SDK harness on Kaggle) must produce finished deliverables, which a judge model grades against an expert-written checklist of binary criteria. A trial passes only when every criterion passes, and each model gets five attempts per task; the score is the share of passing trials. The track has 50 tasks across five subfields and 2,785 rubric criteria, with a median of 49 per task. These results are display-only and do not enter overall or category rankings. DAYJOB Healthcare is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula. ## Leaderboard (19 source rows) | Rank | Model | Configuration | Creator | Score | |------|-------|---------------|---------|-------| | 1 | [Claude Opus 5.5](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Max Reasoning; Evaluated 2026-11-03 | — | 25.2% | | 2 | [Claude Sonnet 5.5](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Max Reasoning; Evaluated 2026-11-03 | — | 16.0% | | 3 | [Gemini 4 Carbon](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | High Reasoning; Evaluated 2026-11-03 | — | 15.6% | | 4 | [Gemini 4 Argon](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | High Reasoning; Evaluated 2026-11-03 | — | 11.6% | | 5 | [GPT-6 Astra](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Max Reasoning; Evaluated 2026-11-03 | — | 11.2% | | 6 | [GPT-6.1 Sol](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Max Reasoning; Evaluated 2026-11-03 | — | 10.8% | | 7 | [Claude Opus 5](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Max Reasoning; Evaluated 2026-11-03 | — | 9.2% | | 8 | [GPT-6 Sol](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Max Reasoning; Evaluated 2026-11-03 | — | 2.8% | | 9 | [GPT-5.6 Terra](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | XHigh Reasoning; Evaluated 2026-11-03 | — | 2.0% | | 10 | [Gemini 3.8 Flash](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | High Reasoning; Evaluated 2026-11-03 | — | 1.2% | | 11 | [GPT-5.6 Luna](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Max Reasoning; Evaluated 2026-11-03 | — | 1.2% | | 12 | [GPT-5.6 Sol](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Max Reasoning; Evaluated 2026-11-03 | — | 1.2% | | 13 | [GPT-6 Luna](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Max Reasoning; Evaluated 2026-11-02 | — | 1.2% | | 14 | [Claude Opus 4.8](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Max Reasoning; Evaluated 2026-11-03 | — | 0.8% | | 15 | [Claude Sonnet 5](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Max; Evaluated 2026-11-03 | — | 0.0% | | 16 | [Gemini 3 Flash Preview](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Gemini 3 Flash High Reasoning; Evaluated 2026-11-02 | — | 0.0% | | 17 | [Gemini 3.1 Pro Preview](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | High Reasoning; Evaluated 2026-11-03 | — | 0.0% | | 18 | [Gemini 3.5 Flash-Lite](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | High Reasoning; Evaluated 2026-11-02 | — | 0.0% | | 19 | [GPT-5.5](https://www.kaggle.com/benchmarks/surge-ai/dayjob-healthcare) | Xhigh Reasoning; Evaluated 2026-11-03 | — | 0.0% | ## FAQ ### What does DAYJOB Healthcare measure? The healthcare track of Surge AI's DAYJOB: 50 long clinical, pharmacy, payer and quality-assurance assignments that an agent must complete to an expert checklist. ### Which source row has the highest reported DAYJOB Healthcare value? Claude Opus 5.5 has the highest reported DAYJOB Healthcare value at 25.2%. These are published source configurations. Compare the disclosed settings before treating a score difference as a model difference. ### How many models are evaluated on DAYJOB Healthcare? The Latest evaluation November 3, 2026 contains 19 AI models. ### Does DAYJOB Healthcare affect BenchLM's overall score? Not directly. DAYJOB Healthcare is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.