AdaPlanBench - Effectiveness: leaderboard

Metric: Effectiveness rubric (1-5): whether the plan, carried out as written, would achieve the goal; mean score (1-5) from three rubric judges (GPT-4.1, DeepSeek-V3.2, Qwen3.6-Flash) over the agent's plans, 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: Estimated already saturated. 10 models tracked.

Top models

#ModelScore
1GPT-54.57
2GPT-5 Mini4.37
3Gemini 3.1 Pro (Preview)4.06
4Gemini 3 Flash4
5GPT-5 Nano3.97
6DeepSeek V4 Flash3.87
7Llama 3.3 70B Instruct3.24
8Qwen 3 32B3.09
9Qwen 3 14B3.03
10Qwen 3 8B2.96

Interactive version: theaggregate.ai/benchmark?slug=adaplanbench-effectiveness · How It Works · Data refreshed daily, snapshot 2026-09-29.