Pause-and-Think-B - Goal Planning: leaderboard

Metric: Binary validity accuracy (%) on the 200 goal-planning items (next-step action suggestion), GPT-5.1 judge, three runs; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 11 models tracked.

Top models

#ModelScore
1GPT-5.286.52
2Qwen 3 VL 235B A22B Instruct72.26
3Gemini 2.5 Pro69.85
4GPT-4o68.13
5Qwen 3 VL 4B Instruct53.76

Interactive version: theaggregate.ai/benchmark?slug=pause-and-think-b-goal-planning · How It Works · Data refreshed daily, snapshot 2026-09-29.