WatchAct - Implicit Intent Inference: 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; instance-weighted mean of the Nonverbal Cue and Reference Disambiguation tasks, 455 instances). Source: arxiv.org. Saturation forecast: Around July 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 32.4 |
| 2 | Gemini 3 Flash | 27.8 |
| 3 | GPT-5.4 | 20.7 |
| 4 | Qwen 3 VL 235B A22B (Thinking) | 12.6 |
| 5 | GPT-5.1 | 12.4 |
| 6 | Gemini 3.1 Flash Lite | 6.4 |
| 7 | Qwen 3 VL 235B A22B Instruct | 5.3 |
Interactive version: theaggregate.ai/benchmark?slug=watchact-implicit-intent-inference · How It Works · Data refreshed daily, snapshot 2026-09-26.