MADE - Jaccard: leaderboard
Label-set agreement on MADE (2026), a living multi-label benchmark of FDA medical device adverse event reports with 1,154 hierarchical labels: the per-report Jaccard index between predicted and gold label sets, averaged over the test reports, with models prompted with ten kNN-retrieved training reports. Percent; higher is better.
Metric: Sample-level Jaccard index (%, the 0-1 score times 100) between the predicted and gold label sets with ten-shot prompting with kNN-retrieved training reports, the task instructions and the label list, on the 10,288-report stratified (truncated) MADE test set of FDA medical device adverse event reports from July 2024 to June 2025 with 1,154 hierarchical IMDRF product and patient problem labels, greedy decoding (GPT-5 at its default medium reasoning effort); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5 | 57 | #178 | |
| 2 | GPT-4.1 | 57 | #505 | |
| 3 | DeepSeek R1 0528 | 50 | #428 | |
| 4 | Qwen 3 235B A22B Instruct | 49 | #691 | |
| 5 | Qwen 3 235B A22B | Thinking | 48 | #628 |
| 6 | Qwen 3 30B A3B | Thinking | 47 | #1156 |
| 7 | Llama-3.3-nemotron-super-49B-v1.5 | 46 | #920 | |
| 8 | GPT-OSS-120B | 45 | #704 | |
| 9 | GLM 4.5 Air | 44 | #886 | |
| 10 | Llama 3.1 70B Instruct | 43 | #1571 | |
| 11 | Qwen 3 4B | Reasoning | 43 | #2348 |
| 12 | Qwen 3 30B A3B Instruct | 43 | #1053 | |
| 13 | Qwen 3 4B Instruct | 41 | #1696 | |
| 14 | Llama 3.1 8B Instruct | 22 | #4600 | |
| 15 | Kimi K2 | 7 | #443 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=made-jaccard · How It Works · Data refreshed daily, snapshot 2026-11-21.