DPrivBench - Gaussian Mechanism (GDP): leaderboard

Differential privacy verification for the Gaussian mechanism under Gaussian 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 Gaussian mechanism instances under Gaussian DP 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

#ModelSettingScoreOverall rank
1Gemini 3 Pro99.6#145
2GPT-5High97.6#178
3DeepSeek V3.1Non-reasoning95.1#511
4DeepSeek R192.9#482
5Claude Sonnet 4.581.4#261
6Claude Opus 4.575.3#160
7Gemini 2.5 Flash74.3#463
8Goedel-Prover-V2-32B59.6
9Qwen 3 30B A3B 2507 Instruct56.7#1100
10Qwen 3 30B A3B 2507 (Thinking)54.5#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-gaussian-mechanism-gdp · How It Works · Data refreshed daily, snapshot 2026-11-21.