ADRD-Bench - Caregiving QA: leaderboard
Metric: Exact-match accuracy (0-1, shown times 100) on 149 caregiving questions (120 true/false and 29 multiple-choice) derived from the Aging Brain Care program's caregiver education materials and reviewed by a senior clinician, pooled over all items; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 36 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 (2026-04-23) | 95.97 | #21 |
| 2 | Claude Opus 4.7 | 95.3 | #45 |
| 3 | Gemini 3.1 Pro (Preview) | 93.96 | #54 |
| 4 | GPT-5.2 | 93.96 | #105 |
| 5 | Qwen 3 235B A22B 2507 Instruct | 93.29 | #291 |
| 6 | Llama 3.1 70B Instruct | 92.62 | #548 |
| 7 | Claude Opus 4.5 (20251101) | 92.62 | #70 |
| 8 | Qwen 3 Max (2025-09-23) | 91.95 | #249 |
| 9 | Gemma 3 12B (IT) | 90.6 | #655 |
| 10 | Qwen 2.5 72B Instruct | 89.93 | #436 |
| 11 | Phi-3-medium-4k-instruct | 89.26 | #939 |
| 12 | Grok 4.1 Fast (Non-reasoning) | 88.59 | #208 (Grok 4.1 Fast) |
| 13 | Qwen 3 30B A3B 2507 Instruct | 87.92 | #464 |
| 14 | Qwen 3 4B 2507 Instruct | 87.25 | #745 |
| 15 | Qwen 2.5 7B Instruct | 85.91 | #846 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=adrd-bench-caregiving-qa · How It Works · Data refreshed daily, snapshot 2026-10-11.