PlanningBench — leaderboard
Metric: All-pass (%) (self-reported). Source: benchmarklist.com. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (xHigh) | 63.17 |
| 2 | Gemini 3.1 Pro (Preview) | 53.25 |
| 3 | DeepSeek V3.2 | 37.13 |
| 4 | Hy3-preview | 36.17 |
| 5 | Qwen 3.5 Plus (Thinking) | 34.03 |
| 6 | Gemini 2.5 Pro | 31.7 |
| 7 | DeepSeek V3.2 Exp | 29.27 |
| 8 | Seed 1.8 | 22.4 |
| 9 | Qwen 3 32B | 0.27 |
| 10 | Qwen 3 8B | 0 |
| 11 | Qwen 3 14B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=planningbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.