PM-AGI - Question Type - Action Based — leaderboard
Metric: Score (%). Source: huggingface.co. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 97.3 |
| 2 | GPT-5.2 | 94.3 |
| 3 | GPT-5.4 | 93.8 |
| 4 | Gemini 2.5 Pro | 82.3 |
| 5 | Gemini 2.5 Flash | 82 |
| 6 | Gemini 3 Flash (Preview) | 80.7 |
| 7 | GPT-5.5 | 50.2 |
Interactive version: theaggregate.ai/benchmark?slug=pm-agi-question-type-action-based · How the rankings work · Data refreshed daily, snapshot 2026-07-22.