MedBench v5 — leaderboard
Metric: CCR-Agent (self-reported). Source: benchmarklist.com. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 96.66 |
| 2 | GPT-5.5 | 95.09 |
| 3 | GLM-5.1 | 94.89 |
| 4 | Grok 4.20 | 94.6 |
| 5 | Gemini 3.1 Pro (Preview) | 94.42 |
| 6 | DeepSeek V4 Pro | 93.12 |
| 7 | Seed 2.0 Pro | 92.44 |
Interactive version: theaggregate.ai/benchmark?slug=medbench-v5 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.