SPADE Zero Shot - EvoBench PubMed AUROC: leaderboard
The SPADE paper compares six zero-shot AI-text detectors using three released language-model backbones. AUROC and true-positive rate at 5% false positives remain separate. Paired base/instruct checkpoints are retained for Binoculars and Fast-DetectGPT. Learned soft prompts and supervised detector weights are distinct artifacts. This board reports aUROC (%). Higher is better.
Metric: AUROC (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 18 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | SPADE Fast-DetectGPT: Falcon-7B + Falcon-7B-Instruct | Evaluation run: frozen two-checkpoint detector | 91.5 | |
| 2 | SPADE Binoculars: Falcon-7B + Falcon-7B-Instruct | Evaluation run: frozen two-checkpoint detector | 91.2 | |
| 3 | Qwen3-8B-Base (Harness: SPADE zero-shot Likelihood) | 90.8 | ||
| 4 | Qwen3-8B-Base (Harness: SPADE zero-shot Entropy) | 90.7 | ||
| 5 | Qwen3-8B-Base (Harness: SPADE zero-shot DNA-GPT) | 87.5 | ||
| 6 | SPADE Fast-DetectGPT: Llama 3.1 8B + Llama 3.1 8B Instruct | Evaluation run: frozen two-checkpoint detector | 87.4 | |
| 7 | SPADE Binoculars: Llama 3.1 8B + Llama 3.1 8B Instruct | Evaluation run: frozen two-checkpoint detector | 86.9 | |
| 8 | Llama 3.1 8B (Harness: SPADE Zero Shot Likelihood) | 82.8 | ||
| 9 | falcon-7B (Harness: SPADE zero-shot Likelihood) | 82.7 | ||
| 10 | Llama 3.1 8B (Harness: SPADE Zero Shot DNA GPT) | 82.2 | ||
| 11 | falcon-7B (Harness: SPADE zero-shot DNA-GPT) | 81.3 | ||
| 12 | Llama 3.1 8B (Harness: SPADE Zero Shot Entropy) | 76.7 | ||
| 13 | SPADE Fast-DetectGPT: Qwen3-8B-Base + Qwen3-8B | Evaluation run: frozen two-checkpoint detector | 71.3 | |
| 14 | SPADE Binoculars: Qwen3-8B-Base + Qwen3-8B | Evaluation run: frozen two-checkpoint detector | 69.1 | |
| 15 | falcon-7B (Harness: SPADE zero-shot Entropy) | 67.9 |
Interactive version: theaggregate.ai/benchmark?slug=spade-zero-shot-evobench-pubmed-auroc · How It Works · Data refreshed daily, snapshot 2026-11-16.