WatchAct - Fine-Grained Action: leaderboard

Metric: Plan success rate (%; the VLM's high-level Pick/Place/Open/Close plan, predicted from a real human video and an instruction, run through a symbolic executor and checked against the task's success predicate; 225 instances). Source: arxiv.org. Saturation forecast: Around April 2027. 9 models tracked.

Top models

#ModelScore
1GPT-5.436.4
2Gemini 3.1 Pro (Preview)33.8
3GPT-5.130.2
4Gemini 3 Flash29.3
5Qwen 3 VL 235B A22B (Thinking)18.2
6Gemini 3.1 Flash Lite8
7Qwen 3 VL 235B A22B Instruct4.9

Interactive version: theaggregate.ai/benchmark?slug=watchact-fine-grained-action · How It Works · Data refreshed daily, snapshot 2026-09-26.