HealthAdminBench: leaderboard
Healthcare administration agent benchmark for prior authorization, appeals, durable medical equipment, payer portals, fax, and EHR-adjacent workflows.
Metric: Success Rate (%). Source: som-shahlab.github.io. Source: leaderboard.steel.dev. Saturation forecast: Around May 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 51.9 | #37 |
| 2 | Claude Mythos 5 | 51.9 | #2 |
| 3 | Claude Mythos Preview | 47.4 | #4 |
| 4 | Claude Sonnet 4.6 | 45.2 | #90 |
| 5 | Kimi K2.5 | 15.6 | #144 |
| 6 | Claude Opus 4.6 | 14.8 | #63 |
| 7 | Qwen 3.5 27B | 13.3 | #187 |
| 8 | Gemini 3.1 Pro (Preview) | 11.9 | #58 |
| 9 | GPT-5.4 | 5.9 | #79 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=healthadminbench · How It Works · Data refreshed daily, snapshot 2026-10-20.