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

#ModelSettingScoreOverall rank
1Gemini 2.5 Flash100#466
2Gemini 3 Pro100#146
3GPT-5High100#185
4Qwen 3 30B A3B 2507 Instruct99.2#1106
5DeepSeek V3.1Non-reasoning99.2#511
6Qwen 3 30B A3B 2507 (Thinking)97.3#769
7Claude Opus 4.595.5#165
8Claude Sonnet 4.594.9#267
9DeepSeek R193.3#484
10Goedel-Prover-V2-32B87.3

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.