PDP-Bench — leaderboard
Metric: Macro-F1 (self-reported). Source: benchmarklist.com. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 78.53 |
| 2 | Claude Opus 4.6 | 73.38 |
| 3 | DeepSeek V4 Pro | 69.22 |
| 4 | GPT-5.4 | 68.99 |
| 5 | Qwen 3.5 35B A3B | 65.64 |
| 6 | GPT-OSS-20B | 57.23 |
Interactive version: theaggregate.ai/benchmark?slug=pdp-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.