CoCoBench - Construct Score: leaderboard
Metric: Construct score (0-100): construct-specific score of how well the target coordination construct is handled, printed 0-1 and scaled by 100; 897 oracle-validated executable household multi-agent task instances with two to four agents, centralized planner with image observations, task-specific step budgets. Source: arxiv.org. Saturation forecast: Around December 2026. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 90 |
| 2 | Claude Opus 4.8 | 87 |
| 3 | Claude Haiku 4.5 | 71 |
| 4 | Kimi K2.6 | 71 |
| 5 | Qwen 3.6 Plus | 70 |
| 6 | Qwen 3.5 9B | 63 |
| 7 | Qwen 3 VL 8B Instruct | 57 |
| 8 | GPT-5.4 Mini | 51 |
Interactive version: theaggregate.ai/benchmark?slug=cocobench-construct-score · How It Works · Data refreshed daily, snapshot 2026-09-26.