DAYJOB: Healthcare
Professional Work · 2026-09-23
Surge AI DAYJOB: Healthcare evaluates professional judgment on 50 expert-designed healthcare assignments in rich file environments. Each task requires complete rubric satisfaction. The leaderboard averages task rewards over five attempts, excludes errored trials, and reports the unweighted mean across tasks. Runs use the DAYJOB OpenHands SDK harness in Harbor with no browsing or package downloads and Claude Opus 4.8 agentic grading.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5.5 | 24.7 |
| GPT-6 Astra | 11.6 |
| Claude Fable 5.1 | 9.6 |
| Claude Opus 5 | 8.4 |
| Grok 4.7 | 8.4 |
| Muse Spark 1.3 | 7.8 |
| Claude Fable 5 | 5.6 |
| GPT-6 Sol | 3.6 |
| Grok 4.6 | 2.8 |
| Muse Spark 1.2 | 2.0 |
| GPT-5.6 Sol | 1.6 |
| GPT-5.6 Terra | 1.6 |
| Kimi K3 | 1.2 |
| Gemini 3.8 Flash | 0.8 |
| GLM-5.3 Flash | 0.4 |
| GLM-5.3 | 0.4 |
| GPT-5.6 Luna | 0.4 |
| Hy3 | 0.4 |
| Sonnet 5 | 0.0 |
| Gemini 3.1 Pro Preview | 0.0 |
| Gemini 3.7 Flash | 0.0 |
| GPT-6 Luna | 0.0 |
| Inkling | 0.0 |
| Kimi K2.7 Code | 0.0 |
| Mistral Large 3 675B Instruct 2512 | 0.0 |
| Muse Glimmer 30B | 0.0 |