PM-AGI - Reasoning Type - Adversarial: leaderboard
The "Reasoning Type - Adversarial" subtask of PM-AGI. Hawky AI's product-marketing benchmark scoring LLMs on realistic digital-marketing and product-management scenarios (Google Ads, Meta Ads, diagnostics, creative strategy) with MCQ and action-based questions.
Metric: Score (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 100 | #245 |
| 2 | GPT-5.4 | 100 | #79 |
| 3 | GPT-5.2 | 100 | #110 |
| 4 | GPT-5.5 | 100 | #31 |
| 5 | Gemini 3 Flash (Preview) | 100 | #82 |
| 6 | Gemini 2.5 Pro | 98.8 | #152 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=pm-agi-reasoning-type-adversarial · How It Works · Data refreshed daily, snapshot 2026-10-20.