Are LLMs Ready to Assist Physicians? PhysAssis: leaderboard
The most plausible near-term role of medical LLMs is to assist rather than replace physicians, yet current evaluations often test isolated capabilities: clinical knowledge, EHR system interaction, or patient communication. Physician assistance instead requires coordinating these capabilities within the same interaction, where physicians issue underspecified requests, patients describe symptoms amb
Metric: en_mrs (self-reported). Source: benchmarklist.com. Saturation forecast: Around July 2027. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5 | 69.4 | #141 |
| 2 | Claude Opus 4.7 | 68.3 | #49 |
| 3 | Kimi K2.6 | 68 | #104 |
| 4 | Seed 1.8 | 67.4 | #139 |
| 5 | Qwen 3.5 35B A3B | 66.3 | #256 |
| 6 | GPT-5.4 (High) | 64.1 | #79 (GPT-5.4) |
| 7 | MiniMax-M2.7 | 63.2 | #258 |
| 8 | Gemini 3.1 Pro (Preview) | 62.1 | #58 |
| 9 | Qwen 3.5 27B | 58.3 | #187 |
| 10 | GPT-5.4 Mini | 57.8 | #212 |
| 11 | Qwen 3.5 9B | 55.2 | #379 |
| 12 | Qwen 3.5 4B | 48.7 | #475 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=are-llms-ready-to-assist-physicians-physassis · How It Works · Data refreshed daily, snapshot 2026-10-20.