DPrivBench - Mechanism Level: leaderboard
Differential privacy verification on the mechanism-level instances of DPrivBench (2026), where the model decides whether a stated differential privacy guarantee holds for a textbook mechanism instantiated with a concrete query, no tools, five seeds: mean accuracy over the six mechanism tasks (Laplace, Gaussian under GDP and zCDP, and three report-noisy-max variants). Percent; higher is better.
Metric: Accuracy (0-1, times 100) on the six mechanism tasks (mean of the per-task accuracies) of the DPrivBench Category 1 mechanism-level instances (a mechanism template instantiated with a concrete query function from a 49-function bank; positive instances calibrate the noise to the true sensitivity, paired negatives under-calibrate it); binary yes/no verdict on whether the stated differential privacy guarantee holds, five seeds, no tools; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5 | High | 99.5 | #178 |
| 2 | Gemini 3 Pro | 92.3 | #145 | |
| 3 | DeepSeek V3.1 | Non-reasoning | 84.1 | #511 |
| 4 | Gemini 2.5 Flash | 77.8 | #463 | |
| 5 | DeepSeek R1 | 74.1 | #482 | |
| 6 | Claude Sonnet 4.5 | 73.8 | #261 | |
| 7 | Claude Opus 4.5 | 72.8 | #160 | |
| 8 | Qwen 3 30B A3B 2507 Instruct | 67.1 | #1100 | |
| 9 | Goedel-Prover-V2-32B | 62.8 | ||
| 10 | Qwen 3 30B A3B 2507 (Thinking) | 56.5 | #764 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=dprivbench-mechanism-level · How It Works · Data refreshed daily, snapshot 2026-11-21.