PlanBench-XL — leaderboard
Metric: Accuracy (%) (self-reported). Source: benchmarklist.com. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 77.06 |
| 2 | DeepSeek V4 Flash | 63.08 |
| 3 | Gemini 3.5 Flash | 52.19 |
| 4 | GPT-5.4 | 51.9 |
| 5 | Llama 3.3 70B Instruct | 18.96 |
| 6 | GPT-5.4 Mini | 3.07 |
| 7 | Qwen 3 32B | 2.75 |
| 8 | Qwen 3 14B | 0.92 |
| 9 | Llama 3.1 8B Instruct | 0 |
| 10 | Qwen 3 8B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=planbench-xl · How the rankings work · Data refreshed daily, snapshot 2026-07-22.