ObGynLongBench - History-Level EHR: leaderboard
Metric: Accuracy (%; full pre-decision EHR history). Source: arxiv.org. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 68.7 |
| 2 | GPT-5.4 Mini | 64.9 |
| 3 | DeepSeek V4 Flash | 64.4 |
| 4 | Qwen 3.5 35B A3B (Non-reasoning) | 60.1 |
| 5 | Claude Haiku 4.5 | 59.8 |
| 6 | Qwen 3 VL 4B | 59.8 |
| 7 | Lingshu-7B | 59.6 |
| 8 | Qwen 3.5 4B (Non-reasoning) | 59.4 |
| 9 | Qwen 3.5 9B (Non-reasoning) | 59.3 |
| 10 | Gemma 4 E4B (Non-reasoning) | 52 |
| 11 | Phi-4 Mini Instruct | 51.1 |
| 12 | MedGemma 1.5 4B | 41.3 |
Interactive version: theaggregate.ai/benchmark?slug=obgynlongbench-history-level-ehr · How It Works · Data refreshed daily, snapshot 2026-09-19.