DAYJOB: Healthcare: leaderboard
DAYJOB: Healthcare (Surge AI, 2026): 50 expert-designed healthcare assignments across clinical, operational, payer, pharmacy and compliance workflows. Each starts from a brief handoff (prompts average 49 words) backed by 19.8 supporting files on average and represents an estimated 13.6 hours of professional work. An agent works through the files in a sandboxed container (Harbor tasks, OpenHands-based harness, network limited to the model API) and has to work out what the request needs: "Rather than telling models exactly what to do, it asks whether agents can figure out what needs to be done, and reason through it until the end." Unlike MedQA-style licensing-exam questions or HealthBench's rubric-graded health conversations, it grades end-to-end agentic work over patient and operations records against a task-specific rubric (median 47.5 criteria per task). Score: the percentage of tasks passed with 100% of rubric criteria satisfied, five attempts per task, Claude Opus 4.8 as the autograder; reasoning effort as labelled. Higher is better. Source: https://surgehq.ai/benchmarks/dayjob-healthcare
Metric: Pass rate at a 100% rubric threshold (%). Source: surgehq.ai. Saturation forecast: Around March 2028. 38 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5.1 (Max) | 31.2 | #10 (Claude Fable 5.1) |
| 2 | Muse Wonder (Max) | 31.2 | #18 (Muse Wonder) |
| 3 | GPT-6 Astra (Max) | 28.4 | #6 (GPT-6 Astra) |
| 4 | Grok 4.7 (xHigh) | 27.6 | #26 (Grok 4.7) |
| 5 | GPT-6.1 Sol (Max) | 25.2 | #7 (GPT-6.1 Sol) |
| 6 | Gemini 4 Argon (High) | 23.6 | #9 (Gemini 4 Argon) |
| 7 | Muse Spark 1.3 (Max) | 22 | #31 (Muse Spark 1.3) |
| 8 | Grok 4.6 (xHigh) | 14.8 | #29 (Grok 4.6) |
| 9 | Muse Spark 1.2 (xHigh) | 8.8 | #69 (Muse Spark 1.2) |
| 10 | GPT-6 Sol (Max) | 7.2 | #19 (GPT-6 Sol) |
| 11 | Hy4 preview (High) | 6.4 | #45 (Hy4 preview) |
| 12 | DeepSeek V4.1 Flash (1017) (Max) | 6 | #27 (DeepSeek V4.1 Flash (1017)) |
| 13 | Qwen 3.8 Max (xHigh) | 4.8 | #34 (Qwen 3.8 Max) |
| 14 | GPT-5.6 Sol (Max) | 4.4 | #22 (GPT-5.6 Sol) |
| 15 | GLM-5.3 (Max) | 4.4 | #44 (GLM-5.3) |
Interactive version: theaggregate.ai/benchmark?slug=dayjob-healthcare · How It Works · Data refreshed daily, snapshot 2026-11-05.