DPrivBench - Laplace Mechanism: leaderboard
Differential privacy verification for the Laplace mechanism (pure differential privacy) 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. Accuracy in percent; higher is better.
Metric: Accuracy (0-1, times 100) on the Laplace mechanism (pure DP) instances 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 | Gemini 2.5 Flash | 100 | #466 | |
| 2 | Gemini 3 Pro | 100 | #146 | |
| 3 | GPT-5 | High | 100 | #185 |
| 4 | Qwen 3 30B A3B 2507 Instruct | 99.2 | #1106 | |
| 5 | DeepSeek V3.1 | Non-reasoning | 99.2 | #511 |
| 6 | Qwen 3 30B A3B 2507 (Thinking) | 97.3 | #769 | |
| 7 | Claude Opus 4.5 | 95.5 | #165 | |
| 8 | Claude Sonnet 4.5 | 94.9 | #267 | |
| 9 | DeepSeek R1 | 93.3 | #484 | |
| 10 | Goedel-Prover-V2-32B | 87.3 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=dprivbench-laplace-mechanism · How It Works · Data refreshed daily, snapshot 2026-11-22.