MECoBench - Completion Rate: leaderboard
Metric: Completion rate (%, mean fraction of subgoals completed) averaged over the parallel and sequential settings with two agents, on 96 VirtualHome household rearrangement tasks (2 to 7 subgoals each) in which multimodal agents act from four-view first-person observations; agents exchange one broadcast message each before acting; printed 0-1 and x100 here; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 94.2 |
| 2 | Gemma 4 31B (IT) | 92.5 |
| 3 | Qwen 3.5 27B | 92.1 |
| 4 | Qwen 3.5 9B | 91.5 |
| 5 | Gemma 4 26B A4B (IT) | 89.2 |
| 6 | Gemini 3.1 Pro (Preview) | 88.1 |
| 7 | Qwen 3 VL 235B A22B Instruct | 78.6 |
| 8 | Qwen 3 VL 32B Instruct | 77.7 |
| 9 | GLM-4.6V | 58.9 |
| 10 | Qwen 3 VL 8B Instruct | 55.1 |
| 11 | Llama 4 Scout Instruct | 38.4 |
Interactive version: theaggregate.ai/benchmark?slug=mecobench-completion-rate · How It Works · Data refreshed daily, snapshot 2026-09-29.