HELM MedHELM - ADHD-Behavior: leaderboard
HELM MedHELM ADHD-Behavior task, identifying behavioral-intervention guidance in pediatric ADHD clinical notes.
Metric: EM. Source: crfm.stanford.edu. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o (2024-05-13) | 83.69 | #325 |
| 2 | O4 Mini (2025-04-16) | 82.98 | #179 |
| 3 | DeepSeek R1 | 80.85 | #251 |
| 4 | GPT-4o Mini (2024-07-18) | 80.61 | #558 |
| 5 | Claude 3.7 Sonnet (20250219) | 80.14 | #201 |
| 6 | O3 Mini (2025-01-31) | 79.91 | #240 |
| 7 | GPT-5 | 78.96 | #98 |
| 8 | Claude 3.5 Sonnet (20241022) | 76.83 | #291 |
| 9 | Gemini 1.5 Pro (001) | 76.12 | #444 |
| 10 | Gemini 2.0 Flash | 72.81 | #342 |
| 11 | Gemini 2.5 Pro (Preview 05-06) | 71.39 | #147 |
| 12 | GPT-5 Mini (2025-08-07) | 68.79 | #172 |
| 13 | Llama 3.3 70B Instruct | 64.07 | #534 |
Interactive version: theaggregate.ai/benchmark?slug=helm-medhelm-adhd-behavior · How It Works · Data refreshed daily, snapshot 2026-10-20.