DeepPlanning: leaderboard
Planning benchmark for complex multi-step tasks that require decomposing goals, tracking constraints, and revising a plan over a long reasoning horizon.
Metric: Score (%). Source: llm-stats.com. Status: years away from saturation. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.7 Plus | 62.3 |
| 2 | Qwen 3.6 Plus | 41.5 |
| 3 | Qwen 3.5 397B A17B | 34.3 |
| 4 | Qwen 3.6 35B A3B | 25.9 |
| 5 | Qwen 3.5 122B A10B | 24.1 |
| 6 | Qwen 3.5 35B A3B | 22.8 |
| 7 | Qwen 3.5 27B | 22.6 |
| 8 | Qwen 3.5 9B | 18 |
| 9 | Qwen 3.5 4B | 17.6 |
Interactive version: theaggregate.ai/benchmark?slug=deepplanning · How It Works · Data refreshed daily, snapshot 2026-09-05.