GMP - Dynamic Rules (Shopping Platform Reviews): leaderboard
Metric: F1 (x100) of the unsafe judgement under GMP Task B rule set 3, Shopping Platform Reviews (delayed, non-anonymous; 2,000 posts judged against that context's listed prohibitions, everything else permitted), zero-shot prompt with JSON output; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 VL 72B Instruct | 77.85 | #364 |
| 2 | Claude Sonnet 4 | 77.03 | #194 |
| 3 | Gemini 2.5 Flash | 76.08 | #237 |
| 4 | DeepSeek V3.1 (Non-reasoning) | 76.04 | #260 (DeepSeek V3.1) |
| 5 | Qwen 3 30B A3B 2507 Instruct | 75.75 | #464 |
| 6 | GPT-4o Mini | 75.71 | #588 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=gmp-dynamic-rules-shopping-platform-reviews · How It Works · Data refreshed daily, snapshot 2026-10-11.