AdaPlanBench: leaderboard
Metric: Accuracy (%): share of tasks whose final plan satisfies every world and user constraint and passes the rubric threshold on every planning dimension (early stops and turn-limit runs fail), 307 household planning tasks with progressively revealed world and user constraints at the mid-level constraint profile: a hidden constraint is disclosed only when a proposed plan violates it (GPT-5.4 constraint judges), and the agent re-plans within the turn budget; temperature 0 (GPT-5 family at its fixed default, mean of three runs); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 67.75 |
| 2 | GPT-5 Mini | 61.89 |
| 3 | Gemini 3 Flash | 43.32 |
| 4 | GPT-5 Nano | 42.35 |
| 5 | DeepSeek V4 Flash | 35.53 |
| 6 | Gemini 3.1 Pro (Preview) | 34.53 |
| 7 | Llama 3.3 70B Instruct | 29.32 |
| 8 | Qwen 3 32B | 17.92 |
| 9 | Qwen 3 14B | 17.26 |
| 10 | Qwen 3 8B | 14.38 |
Interactive version: theaggregate.ai/benchmark?slug=adaplanbench · How It Works · Data refreshed daily, snapshot 2026-09-29.